{"id":"W7106613716","doi":"10.1183/13993003.congress-2025.oa2240","title":"Late Breaking Abstract - Evaluating the accuracy of state-of-the-art large language models in answering asthma multiple choice and objective structured clinical examination questions","year":2025,"lang":"","type":"article","venue":"","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Asthma; Objective structured clinical examination; Multiple choice; Nice; Clinical history; Multiple Models","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01200965,0.002624144,0.001193529,0.001646165,0.0006982803,0.002734581,0.002597062,0.00291754,0.009769625],"category_scores_gemma":[0.03312172,0.000669651,0.003123644,0.0007760996,0.0006354519,0.003049935,0.002364808,0.003206472,0.007331082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002089841,"about_ca_system_score_gemma":0.002310065,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01977644,"about_ca_topic_score_gemma":0.01808613,"domain_scores_codex":[0.9939609,0.003179635,0.0004319492,0.001510855,0.0006437835,0.0002730051],"domain_scores_gemma":[0.9769788,0.01772962,0.000486765,0.001805907,0.002410265,0.0005887049],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.005565587,0.001782532,0.05568082,0.00245809,0.002485685,0.0005939514,0.0007711711,0.1744039,0.008221946,0.002624143,0.1262413,0.6191708],"study_design_scores_gemma":[0.0004614165,0.001121979,0.01172098,0.0004387436,0.0005816031,0.000330581,0.0004076719,0.960262,0.008147701,0.004487897,0.01190272,0.0001366847],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6309021,0.0211175,0.2141828,0.01047988,0.004084202,0.001759736,0.04352086,0.04712517,0.02682776],"genre_scores_gemma":[0.8312786,0.001332754,0.1012507,0.00274927,0.0005987597,0.000765566,0.05216993,0.001036755,0.00881782],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01977644,"threshold_uncertainty_score":0.06351388,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1325214112567897,"score_gpt":0.4914991234810523,"score_spread":0.3589777122242627,"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."}}