{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01702811,0.001024337,0.0009083785,0.001028566,0.001862003,0.001643125,0.001454801,0.00161399,0.005304163],"category_scores_gemma":[0.01951926,0.001100017,0.0009478421,0.0004878257,0.001587973,0.001340476,0.001568798,0.001700511,0.001339844],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001470283,"about_ca_system_score_gemma":0.002885066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001341444,"about_ca_topic_score_gemma":0.002574337,"domain_scores_codex":[0.9930107,0.00424902,0.0005262384,0.000964822,0.000652037,0.0005972906],"domain_scores_gemma":[0.9829323,0.01089283,0.001531931,0.00149152,0.001730329,0.001421111],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"nonrandomized_trial","study_design_gemma":"observational","study_design_scores_codex":[0.01747422,0.3133509,0.1862247,0.006656907,0.0005192395,0.003429602,0.2379482,0.002558925,0.01588329,0.00265425,0.003769612,0.2095301],"study_design_scores_gemma":[0.01312589,0.466383,0.2973529,0.002171436,0.0009900125,0.002203959,0.1537079,0.01316939,0.01789632,0.002713461,0.02967465,0.0006112924],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9916745,0.00006896091,0.001880257,0.00003887147,0.00001611827,0.005637165,0.0001066953,0.0000261539,0.0005514069],"genre_scores_gemma":[0.9481113,0.0002657568,0.01734579,0.000579075,0.00006961606,0.0312193,0.000290893,0.00004713469,0.002071105],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01702811,"threshold_uncertainty_score":0.09005433,"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."}}