{"id":"W4414368365","doi":"10.2196/68070","title":"Evaluating the Potential and Accuracy of ChatGPT-3.5 and 4.0 in Medical Licensing and In-Training Examinations: Systematic Review and Meta-Analysis","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Education","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Reliability (semiconductor); Set (abstract data type); Focus (optics); MEDLINE; Component (thermodynamics); Medical diagnosis","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"],"consensus_categories":[],"category_scores_codex":[0.00366529,0.00009982638,0.0007588811,0.0003107226,0.00007610794,0.00002173384,0.00005293002,0.0001252845,0.0001091462],"category_scores_gemma":[0.01464547,0.00006608321,0.00004988313,0.0007015907,0.0001851355,0.00009405624,0.00004168065,0.0002688395,3.33415e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003730975,"about_ca_system_score_gemma":0.0009172517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004925483,"about_ca_topic_score_gemma":0.0003439471,"domain_scores_codex":[0.9979737,0.0003804824,0.0008230513,0.0002441349,0.0004486994,0.0001298859],"domain_scores_gemma":[0.9979966,0.001300311,0.0002029616,0.000180076,0.0001665186,0.0001535516],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001548076,0.001357135,0.03401848,0.4046475,0.01014611,0.00001680084,0.07354375,0.000006729187,0.0002181385,0.00308816,0.0003732297,0.4724291],"study_design_scores_gemma":[0.0009572909,0.0005262487,0.4005688,0.0967909,0.2901908,0.0005907818,0.105049,0.09743456,0.0001621967,0.006887109,0.00009189356,0.0007504413],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8460422,0.09078135,0.00008486604,0.06149085,0.00007965056,0.001454806,5.789908e-7,0.000006765311,0.00005897724],"genre_scores_gemma":[0.9880418,0.007189455,0.0001856534,0.004216301,0.00003827039,0.000260158,0.000009051751,0.000004398982,0.00005488563],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4716787,"threshold_uncertainty_score":0.9936546,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2479325627637239,"score_gpt":0.5553943139980585,"score_spread":0.3074617512343346,"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."}}