{"id":"W4411242685","doi":"10.2196/77332","title":"Utility of Generative Artificial Intelligence for Japanese Medical Interview Training: Randomized Crossover Pilot Study","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Education","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Preprint; Crossover; Crossover study; Randomized controlled trial; Artificial intelligence; Computer science; Psychology; Medicine; Alternative medicine; Placebo; World Wide Web","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":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004154579,0.0002099738,0.0008828833,0.0002354069,0.0001416383,0.0000262723,0.0002674443,0.0002247998,0.002722752],"category_scores_gemma":[0.01944645,0.0001670473,0.0001930378,0.000558197,0.0005975376,0.00009312572,0.00005047006,0.0004323385,0.00002006725],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009084795,"about_ca_system_score_gemma":0.007725124,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007112537,"about_ca_topic_score_gemma":0.0004340183,"domain_scores_codex":[0.9960749,0.0005294858,0.001695708,0.0004720126,0.0009115476,0.0003163755],"domain_scores_gemma":[0.9963204,0.001634912,0.0002698006,0.0004158162,0.0008920225,0.0004670354],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.03118003,0.01375523,0.001414431,0.0009112235,0.0002084008,0.000002546891,0.04400027,6.088332e-7,0.00005858806,0.01134592,0.005717651,0.8914051],"study_design_scores_gemma":[0.03897909,0.01697319,0.01698668,0.01206585,0.00241972,0.0001282623,0.5380217,0.09684889,0.02525963,0.2375007,0.01279944,0.002016775],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9122328,0.0007236037,0.02798232,0.04595541,0.004009834,0.006952599,0.000005750072,0.00007586122,0.002061851],"genre_scores_gemma":[0.9926381,0.00007705981,0.0004198694,0.003603111,0.000762808,0.001770434,0.00006897792,0.0000152905,0.0006443479],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8893883,"threshold_uncertainty_score":0.9981889,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2738637925591789,"score_gpt":0.5231655511726371,"score_spread":0.2493017586134582,"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."}}