{"id":"W4415155614","doi":"10.3390/ime4040039","title":"Understanding the Role of Large Language Model Virtual Patients in Developing Communication and Clinical Skills in Undergraduate Medical Education","year":2025,"lang":"en","type":"article","venue":"International Medical Education","topic":"Simulation-Based Education in Healthcare","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; McMaster University","funders":"McMaster University","keywords":"Likert scale; Fidelity; Virtual patient; Scale (ratio); Work (physics); Simulated patient; MEDLINE; Communication skills","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001469552,0.000123586,0.0002296915,0.0004945581,0.00007101645,0.00001882484,0.0003030853,0.0002537279,0.0001195654],"category_scores_gemma":[0.006022489,0.0001079174,0.00004736733,0.0004762133,0.0001693064,0.0001453233,0.0001015695,0.0005340357,0.000003347036],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009689222,"about_ca_system_score_gemma":0.009803591,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006395067,"about_ca_topic_score_gemma":0.001032409,"domain_scores_codex":[0.9974169,0.0002716625,0.0009989198,0.0002735602,0.0008636134,0.0001753489],"domain_scores_gemma":[0.9978586,0.001061458,0.0002244737,0.000295856,0.0003882395,0.000171303],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005691744,0.001621834,0.8458692,0.00004540784,0.00002523154,2.629209e-7,0.002453791,0.00004113991,0.000001226214,0.11665,0.0006567706,0.0325782],"study_design_scores_gemma":[0.00236471,0.0000446795,0.8458773,0.002911136,0.00002818636,0.000004981275,0.01367981,0.1003762,0.00002407094,0.03393944,0.0006078819,0.0001415473],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9179239,0.0004386041,0.003422674,0.07417291,0.001196059,0.0005607831,0.000005128531,0.00002007474,0.002259847],"genre_scores_gemma":[0.9907776,0.0005113843,0.0007825334,0.007193008,0.0001103932,0.00008954568,0.0003331744,0.0000124538,0.000189892],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1003351,"threshold_uncertainty_score":0.9958099,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03336576451276652,"score_gpt":0.4442491564292637,"score_spread":0.4108833919164972,"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."}}