{"id":"W4376866715","doi":"10.2196/48291","title":"Large Language Models in Medical Education: Opportunities, Challenges, and Future Directions","year":2023,"lang":"en","type":"article","venue":"JMIR Medical Education","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":659,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Engineering ethics; Curriculum; Misinformation; Competence (human resources); Paradigm shift; Knowledge management; Psychology; Pedagogy; Computer science; Engineering; Computer security; Epistemology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008769456,0.000139838,0.0002182873,0.0004113014,0.0001127857,0.00001556443,0.0001070576,0.0004019935,0.001638309],"category_scores_gemma":[0.000800211,0.0001300021,0.00004165913,0.0005108202,0.00008873869,0.0001849587,0.00003928908,0.0005056154,0.00008720616],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001580645,"about_ca_system_score_gemma":0.008831689,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004171719,"about_ca_topic_score_gemma":0.0008322425,"domain_scores_codex":[0.9980257,0.0001107708,0.0004562321,0.0003312636,0.0007384314,0.0003376094],"domain_scores_gemma":[0.9985229,0.0001184826,0.00006637318,0.0002791194,0.0001633855,0.0008497837],"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":[0.00002141603,0.001014783,0.0006638457,0.0002256938,0.000007612679,0.00001623913,0.03179962,6.517531e-8,0.000001760655,0.01517614,0.02308411,0.9279887],"study_design_scores_gemma":[0.0002113278,0.0001250176,0.02562498,0.0009535537,0.00002605209,0.0002629662,0.2105559,0.003001144,0.00001591817,0.007747708,0.7512181,0.0002573568],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5908596,0.02639184,0.00001651273,0.3630863,0.004035149,0.0007973003,0.000004484407,0.0002554681,0.01455337],"genre_scores_gemma":[0.8720461,0.1031812,0.00009111636,0.01213415,0.006732571,0.001126101,0.0006527168,0.00004217833,0.003993866],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9277313,"threshold_uncertainty_score":0.9992743,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1544938451333391,"score_gpt":0.45587011716273,"score_spread":0.3013762720293909,"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."}}