{"id":"W2991213201","doi":"10.1503/cmaj.190506","title":"Deconstructing the diagnostic reasoning of human versus artificial intelligence","year":2019,"lang":"en","type":"article","venue":"Canadian Medical Association Journal","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":33,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Artificial intelligence, situated approach; Key (lock); Human intelligence; Artificial psychology; Model-based reasoning; Applications of artificial intelligence; Marketing and artificial intelligence; Data science; Cognitive science; Artificial Intelligence System; Intelligent decision support system; Knowledge representation and reasoning; Psychology; Computer security","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01494509,0.0007735942,0.001092507,0.005120074,0.002133104,0.01132233,0.002620429,0.004429066,0.005633242],"category_scores_gemma":[0.03032027,0.000641839,0.0007548638,0.002158852,0.04973361,0.02205036,0.006359571,0.009511167,0.001050988],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006287634,"about_ca_system_score_gemma":0.005365624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004520983,"about_ca_topic_score_gemma":0.003586564,"domain_scores_codex":[0.9903857,0.005974324,0.0004760528,0.0008087871,0.001935504,0.0004196384],"domain_scores_gemma":[0.9614623,0.0306984,0.001370498,0.002393075,0.002622189,0.001453616],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00003352413,0.00001804791,0.0003613266,0.0001174832,0.000009395877,0.0001011176,0.002210349,0.0003966815,0.000110356,0.9794486,0.001484861,0.01570825],"study_design_scores_gemma":[0.000008515856,0.00001201707,0.0002039302,0.0002503309,0.000005485497,0.000132827,0.0008770971,0.0009458386,0.00008652325,0.9814119,0.01605395,0.00001163327],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.03136193,0.08428217,0.3293722,0.3304315,0.00454729,0.0001943962,0.0003311289,0.0004758986,0.2190036],"genre_scores_gemma":[0.8397349,0.02486481,0.1036581,0.01638203,0.005221829,0.0001995659,0.0002516634,0.0002300201,0.009457184],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01494509,"threshold_uncertainty_score":0.07903814,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02452064566032263,"score_gpt":0.3253705643405955,"score_spread":0.3008499186802728,"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."}}