{"id":"W4400227575","doi":"10.2196/preprints.63719","title":"Assessment of Artificial Intelligence Chatbot Performance on the Canadian Otolaryngology and Head and Neck Surgery In-Training Exam: Insights from a Comparative Analysis (Preprint)","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Chatbot; Head and neck surgery; Preprint; Otorhinolaryngology; Computer science; Head and neck; Medicine; Medical education; Artificial intelligence; World Wide Web; Surgery","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.01184,0.0003571696,0.0004695126,0.003025472,0.0009820851,0.001685693,0.0009069934,0.0005643917,0.002765885],"category_scores_gemma":[0.06184269,0.0001589466,0.0005824127,0.002453376,0.0009335628,0.001114033,0.001316246,0.0005793634,0.000772196],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004726334,"about_ca_system_score_gemma":0.002411643,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.09257232,"about_ca_topic_score_gemma":0.124775,"domain_scores_codex":[0.992186,0.003116464,0.0005618006,0.0008217069,0.00272327,0.0005907925],"domain_scores_gemma":[0.9240892,0.04731923,0.004246301,0.001861414,0.01960567,0.002878251],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.003024995,0.001052082,0.8216383,0.0005072179,0.0005144115,0.0003011913,0.02041744,0.003422051,0.002544314,0.0008423838,0.008158633,0.1375771],"study_design_scores_gemma":[0.0000322236,0.0009588014,0.9838039,0.00005363733,0.00009197552,0.0000691646,0.005786648,0.006214475,0.0008551002,0.0001272865,0.001975458,0.00003135113],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9945188,0.0002226377,0.0007339711,0.0001280011,0.00002913066,0.00009636852,0.000483043,0.00005326336,0.00373472],"genre_scores_gemma":[0.9967126,0.00008263682,0.0009744829,0.00003916661,0.00001565358,0.00007472068,0.0009131674,0.00002120917,0.001166309],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9952736,"threshold_uncertainty_score":0.184067,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2940800712309036,"score_gpt":0.4346810910223581,"score_spread":0.1406010197914545,"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."}}