{"id":"W4392621058","doi":"10.2196/57054","title":"Performance of GPT-4V in Answering the Japanese Otolaryngology Board Certification Examination Questions: Evaluation Study","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Education","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Certification; Otorhinolaryngology; Computer science; Board certification; Artificial intelligence; Medical physics; Medicine; Natural language processing; Medical education; Surgery; Continuing medical education","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005513461,0.001102319,0.0008467944,0.001201207,0.0003428483,0.000903263,0.001018015,0.001595116,0.00231119],"category_scores_gemma":[0.02142022,0.000269879,0.0009223238,0.0005713612,0.0005078526,0.001182807,0.001557729,0.0005739675,0.001147205],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000709381,"about_ca_system_score_gemma":0.0007856151,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00423772,"about_ca_topic_score_gemma":0.003326514,"domain_scores_codex":[0.994992,0.002258007,0.0004799054,0.0009032015,0.00100607,0.0003608101],"domain_scores_gemma":[0.9854876,0.009110072,0.0008472062,0.0007681742,0.002791892,0.0009950085],"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":[0.01477035,0.00551842,0.3563604,0.003330143,0.0008079697,0.001217353,0.005404546,0.01303647,0.03217067,0.0004314801,0.01028241,0.5566698],"study_design_scores_gemma":[0.001559717,0.0241028,0.6618857,0.0003121159,0.001120136,0.002737656,0.003053736,0.2668818,0.02978089,0.0007337023,0.007585343,0.0002464091],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9931733,0.0004065041,0.003286116,0.00007478469,0.0000444488,0.0003593445,0.0004705054,0.0005019177,0.001683091],"genre_scores_gemma":[0.9864035,0.0002511912,0.00998942,0.0001276447,0.00004520237,0.0003467546,0.001693418,0.00005119463,0.001091644],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005513461,"threshold_uncertainty_score":0.02915829,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09985689028391924,"score_gpt":0.4674010709257226,"score_spread":0.3675441806418033,"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."}}