{"id":"W4408842496","doi":"10.15173/mumj.v21i1.3674","title":"Integrating large language models into medical education: A commentary on opportunities, challenges, and future directions","year":2025,"lang":"en","type":"article","venue":"McMaster University Medical Journal","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Engineering ethics; Data science; Computer science; Medical education; Psychology; Medicine; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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":[0.0006154063,0.000109574,0.0001823238,0.0002615348,0.0003976906,0.00001943465,0.0001368881,0.0002128896,0.002070617],"category_scores_gemma":[0.0002018042,0.00009513023,0.00005784035,0.0001375269,0.0001071474,0.0001646186,0.00007132349,0.0009181935,0.000004778424],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002522404,"about_ca_system_score_gemma":0.001583406,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002674351,"about_ca_topic_score_gemma":0.0005774858,"domain_scores_codex":[0.9987152,0.0001657416,0.0002435346,0.0001702656,0.0005033025,0.0002020082],"domain_scores_gemma":[0.998859,0.0001386614,0.00006111478,0.0001173993,0.000142642,0.0006811393],"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":[0.0001082091,0.000390197,0.0002928033,0.00007254145,0.00005003433,0.0001617157,0.01218929,8.51096e-8,0.000001057698,0.009325761,0.02633795,0.9510704],"study_design_scores_gemma":[0.000274032,0.00017274,0.000332575,0.001113993,0.00006479837,0.000328116,0.1964557,0.001365139,0.00001185373,0.001275006,0.7985122,0.00009388098],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.06536055,0.01263376,0.002980425,0.8551922,0.002593145,0.0002463036,0.000004676281,0.00007038171,0.06091852],"genre_scores_gemma":[0.6834058,0.133657,0.00196615,0.1574284,0.009643584,0.000006534945,0.0001191273,0.00003775884,0.01373567],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.9509765,"threshold_uncertainty_score":0.9988416,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09127655172895374,"score_gpt":0.3630472839520471,"score_spread":0.2717707322230933,"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."}}