{"id":"W4400079353","doi":"10.2196/59213","title":"A Language Model–Powered Simulated Patient With Automated Feedback for History Taking: Prospective Study","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Education","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":114,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Preprint; Computer science; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007428843,0.0009007775,0.0007173099,0.0008243443,0.001438634,0.001507945,0.001233384,0.00188391,0.004640141],"category_scores_gemma":[0.01757979,0.0008664366,0.0009161517,0.0004351182,0.001480834,0.001281018,0.001502077,0.001927804,0.002075059],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001369357,"about_ca_system_score_gemma":0.00224758,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002134353,"about_ca_topic_score_gemma":0.002375949,"domain_scores_codex":[0.9959706,0.002426655,0.0002520902,0.0005444658,0.0004340585,0.0003721231],"domain_scores_gemma":[0.9879102,0.005308757,0.001575951,0.001734945,0.001405269,0.00206485],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"nonrandomized_trial","study_design_scores_codex":[0.01392596,0.3065135,0.5579898,0.001192976,0.0003542528,0.006024428,0.03922748,0.002681209,0.005024588,0.0008228364,0.00294036,0.06330261],"study_design_scores_gemma":[0.006675285,0.5667863,0.3543783,0.0004219972,0.0005703998,0.005036565,0.03183063,0.01438149,0.007340073,0.0009296915,0.0112047,0.0004445289],"study_design_candidate":"nonrandomized_trial","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.99872,0.00002818056,0.0003207008,0.00003684576,0.000007646296,0.0005771116,0.0000640017,0.00001212212,0.0002335296],"genre_scores_gemma":[0.9955876,0.00009090448,0.001758776,0.0002774672,0.00002645789,0.001502658,0.0002102425,0.00001325728,0.0005325883],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007428843,"threshold_uncertainty_score":0.03928792,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06459609217325434,"score_gpt":0.4453597336472424,"score_spread":0.380763641473988,"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."}}