{"id":"W7093362435","doi":"10.2196/79039","title":"Large Language Model–Based Virtual Patient Systems for History-Taking in Medical Education: Comprehensive Systematic Review","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Unified Medical Language System; Virtual patient; Health informatics; MEDLINE; Representation (politics); Telemedicine; Systematized Nomenclature of Medicine; Disease; Semantics (computer science)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001512139,0.0002273259,0.000785522,0.00028718,0.0000879656,0.00005218866,0.00126502,0.0002634689,0.00005630422],"category_scores_gemma":[0.00360457,0.0001872667,0.0001150738,0.0004460492,0.00005530355,0.0002612382,0.0002848257,0.0006586773,0.00002193538],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000641184,"about_ca_system_score_gemma":0.004045209,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003766256,"about_ca_topic_score_gemma":0.00001735625,"domain_scores_codex":[0.995679,0.0003326445,0.001790074,0.000210243,0.001553238,0.0004347774],"domain_scores_gemma":[0.9971185,0.0007455794,0.0006630979,0.0008010365,0.0003057643,0.000365967],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009840073,0.0004237753,0.00008400135,0.7723265,0.00003784369,0.00002474326,0.01896604,0.001058886,1.770866e-7,0.1534979,0.04608729,0.00748301],"study_design_scores_gemma":[0.0004520638,0.00006390446,0.000007194225,0.1040835,0.00001618826,0.00001613879,0.001349394,0.8891623,3.520167e-7,0.00004125818,0.004654488,0.0001532289],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002916071,0.04301394,0.9340268,0.00726149,0.002665342,0.006578751,0.00001252283,0.000389335,0.00313569],"genre_scores_gemma":[0.6812063,0.001191865,0.03091197,0.2743653,0.0003019377,0.01057436,0.0002900025,0.00007538965,0.001082891],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9031149,"threshold_uncertainty_score":0.7636514,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01912062361534121,"score_gpt":0.3483418598075553,"score_spread":0.3292212361922141,"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."}}