{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04570028,0.0007697535,0.001028558,0.002443551,0.001752259,0.0115618,0.003207553,0.006151091,0.009399696],"category_scores_gemma":[0.06359125,0.0008331128,0.000915073,0.002926217,0.007501942,0.02503715,0.007478152,0.008361751,0.002422402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003779668,"about_ca_system_score_gemma":0.01022265,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007099399,"about_ca_topic_score_gemma":0.009340091,"domain_scores_codex":[0.9817007,0.01431611,0.0006448026,0.0008489151,0.001861506,0.0006278657],"domain_scores_gemma":[0.8684112,0.1126617,0.002365103,0.006402419,0.006370979,0.003788604],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000185404,0.0004427643,0.005564143,0.001484444,0.00005956368,0.0002527772,0.004055961,0.01153135,0.0006901661,0.3922845,0.03661939,0.5468296],"study_design_scores_gemma":[0.00006090745,0.0001708203,0.00124167,0.002488655,0.0000393591,0.0003995896,0.007460677,0.04304119,0.0008773505,0.7516844,0.1923999,0.000135537],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.01300165,0.07156354,0.1482946,0.7388548,0.001173401,0.00013791,0.0003279434,0.00108451,0.0255617],"genre_scores_gemma":[0.4335121,0.1078514,0.4025044,0.03688521,0.005967078,0.0008630715,0.0007980235,0.0004307149,0.0111879],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.04570028,"threshold_uncertainty_score":0.2416891,"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."}}