{"id":"W4412744396","doi":"10.2196/69313","title":"Role of Artificial Intelligence in Surgical Training by Assessing GPT-4 and GPT-4o on the Japan Surgical Board Examination With Text-Only and Image-Accompanied Questions: Performance Evaluation Study","year":2025,"lang":"en","type":"article","venue":"JMIR Medical Education","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Workforce; Medicine; Medical education; Psychology; Artificial intelligence; Computer science; Political science","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":[],"consensus_categories":[],"category_scores_codex":[0.002751524,0.0001570727,0.0002786727,0.000262081,0.0001855179,0.00006464976,0.00008877549,0.0001613794,0.000127022],"category_scores_gemma":[0.001099313,0.0001132881,0.00002150066,0.0006243499,0.0002916102,0.0002271225,0.00002331093,0.0004717575,0.000003225705],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001726602,"about_ca_system_score_gemma":0.00193009,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004647264,"about_ca_topic_score_gemma":0.0001801819,"domain_scores_codex":[0.9975345,0.0004471718,0.0006591224,0.0003685465,0.0007770424,0.0002136491],"domain_scores_gemma":[0.9983725,0.00073448,0.0001616987,0.0002065949,0.0003763855,0.0001483283],"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":[0.0001958985,0.001282966,0.0476861,0.00006874897,0.00001213753,0.000001115571,0.009229207,0.000004609089,0.000139967,0.001510422,0.00004390221,0.9398249],"study_design_scores_gemma":[0.0003424289,0.001212057,0.7923,0.002010325,0.0001236601,0.0000782926,0.1441862,0.05598533,0.001306927,0.001685733,0.000520264,0.0002487419],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9920503,0.0003929742,0.00007851042,0.004766702,0.0001815279,0.001392251,7.29027e-7,0.00002201611,0.001114956],"genre_scores_gemma":[0.9989363,0.0001289781,0.0001379098,0.0001737291,0.0001645468,0.0003732784,0.00003394188,0.00001074032,0.00004059741],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9395762,"threshold_uncertainty_score":0.4619755,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07409362411161255,"score_gpt":0.4485447978764953,"score_spread":0.3744511737648827,"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."}}