{"id":"W4384834592","doi":"10.2196/49034","title":"Effects of Combinational Use of Additional Differential Diagnostic Generators on the Diagnostic Accuracy of the Differential Diagnosis List Developed by an Artificial Intelligence–Driven Automated History–Taking System: Pilot Cross-Sectional Study","year":2023,"lang":"en","type":"article","venue":"JMIR Formative Research","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Japan Society for the Promotion of Science","keywords":"Medical diagnosis; Index (typography); Diagnostic accuracy; Medicine; Data mining; McNemar's test; Medical history; Computer science; Information retrieval; Statistics; World Wide Web; Pathology; Internal medicine; Mathematics","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":[0.02957332,0.0008009303,0.0008850376,0.001571115,0.0005602548,0.00119469,0.0009187011,0.00117872,0.001039663],"category_scores_gemma":[0.07888726,0.0008345903,0.001440108,0.0008606251,0.0009315618,0.001706719,0.001646735,0.00108331,0.0003449926],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007885191,"about_ca_system_score_gemma":0.0006517218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001095802,"about_ca_topic_score_gemma":0.001407641,"domain_scores_codex":[0.9698888,0.01781379,0.003109619,0.003756356,0.004593285,0.0008381628],"domain_scores_gemma":[0.848142,0.1116883,0.01509525,0.01055919,0.01075162,0.003763492],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.009879541,0.004882234,0.9268314,0.0001625814,0.0009720779,0.0003201553,0.001142626,0.001312728,0.003763694,0.00003716066,0.0002021763,0.05049362],"study_design_scores_gemma":[0.0006726406,0.06545264,0.8988245,0.00006050637,0.001475222,0.001448403,0.001001623,0.01856323,0.01145728,0.000139098,0.0007996708,0.0001051305],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9985843,0.0001087842,0.000866205,0.000031807,0.00001324091,0.0001369632,0.00004344074,0.00002252193,0.0001928135],"genre_scores_gemma":[0.995793,0.0000593978,0.003667947,0.00005565414,0.00002716405,0.0001350346,0.0001125332,0.00001237145,0.0001368769],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02957332,"threshold_uncertainty_score":0.1564006,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1704062283172659,"score_gpt":0.4385155011283928,"score_spread":0.268109272811127,"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."}}