{"id":"W4390918905","doi":"10.2196/53961","title":"A Generative Pretrained Transformer (GPT)–Powered Chatbot as a Simulated Patient to Practice History Taking: Prospective, Mixed Methods Study","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Education","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":132,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Chatbot; Conversation; Usability; Computer science; Psychology; Medical education; Medicine; Artificial intelligence; Human–computer interaction; Communication","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":[0.001344869,0.000253303,0.000347618,0.0003616555,0.0001225934,0.00004831318,0.0001188743,0.0002600319,0.002852355],"category_scores_gemma":[0.008359134,0.0002160365,0.0001051141,0.0007806566,0.00008709424,0.0002837849,0.00001768269,0.0006574928,0.0002741866],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00171244,"about_ca_system_score_gemma":0.007690403,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009822397,"about_ca_topic_score_gemma":0.00007315298,"domain_scores_codex":[0.996696,0.0005464328,0.0007805449,0.0006813513,0.0009257818,0.0003698865],"domain_scores_gemma":[0.9973763,0.0006033556,0.0001460362,0.0003517182,0.0007511624,0.00077143],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006381649,0.004833972,0.0003760331,0.000201972,0.0001645012,0.00003422727,0.2307532,0.000005445379,0.001500072,0.0008188112,0.02205385,0.7386197],"study_design_scores_gemma":[0.0004947983,0.009709146,0.007410744,0.001450202,0.0005670294,0.0002674769,0.163917,0.006425463,0.01089285,0.001685068,0.7963787,0.0008015262],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.90187,0.003117886,0.008003229,0.05559017,0.01329352,0.00863291,0.000003083203,0.0004041998,0.009085061],"genre_scores_gemma":[0.9823979,0.00004355796,0.005842974,0.007187779,0.0009766552,0.00157567,0.00005359217,0.00005204499,0.001869795],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7743248,"threshold_uncertainty_score":0.9999939,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08406383022874636,"score_gpt":0.5209060402476431,"score_spread":0.4368422100188967,"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."}}