{"id":"W4392702964","doi":"10.2196/54393","title":"Capability of GPT-4V(ision) in the Japanese National Medical Licensing Examination: Evaluation Study","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Education","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":59,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"McNemar's test; Test (biology); Artificial intelligence; Computer science; Medical physics; Medicine; Mathematics; Statistics","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004740435,0.001151311,0.000684324,0.001195582,0.000216479,0.0007629214,0.001082919,0.001286684,0.001812862],"category_scores_gemma":[0.01476705,0.0002498723,0.0009731891,0.0004573905,0.0004109373,0.001211613,0.001385081,0.0006967892,0.0007948069],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007442116,"about_ca_system_score_gemma":0.0008325371,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004676355,"about_ca_topic_score_gemma":0.004280228,"domain_scores_codex":[0.9978673,0.00102909,0.0001940276,0.0003839466,0.0003941759,0.0001313518],"domain_scores_gemma":[0.9934806,0.004433976,0.0003557537,0.0004707188,0.0007807728,0.0004781771],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.01022648,0.002897732,0.3150031,0.001311165,0.001147714,0.0006650572,0.001259231,0.03495752,0.01664764,0.0005508498,0.008119768,0.6072137],"study_design_scores_gemma":[0.000709434,0.01136428,0.2313308,0.0001483543,0.001023707,0.001845116,0.0008834371,0.7230509,0.02477766,0.001077834,0.003617256,0.0001711749],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9895174,0.0007063238,0.006148815,0.0001375888,0.00005511822,0.0002412045,0.0007658972,0.0007471488,0.001680626],"genre_scores_gemma":[0.9876359,0.0002702319,0.008112155,0.0001010315,0.00003987054,0.0001528266,0.002690384,0.00004598095,0.0009515086],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9952596,"threshold_uncertainty_score":0.02507007,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1563856543944998,"score_gpt":0.5352369858648602,"score_spread":0.3788513314703604,"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."}}