{"id":"W4406000215","doi":"10.2196/63719","title":"Assessment of Artificial Intelligence Chatbot Performance on the Canadian Otolaryngology and Head and Neck Surgery In-Training Exam: Insights from an Experimental Comparative Analysis (Preprint)","year":2024,"lang":"en","type":"article","venue":"JMIR Medical Education","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Otorhinolaryngology; Head and neck surgery; Preprint; Chatbot; Training (meteorology); Medicine; Medical education; Computer science; Psychology; Artificial intelligence; Surgery; World Wide Web; Geography","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":true,"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":[0.007774583,0.0004150181,0.0004407022,0.001136156,0.00112313,0.001475923,0.001087232,0.001012997,0.003789571],"category_scores_gemma":[0.05477459,0.0002767644,0.0003715086,0.0007927204,0.0009269269,0.001096327,0.001280797,0.000962361,0.001186342],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001895936,"about_ca_system_score_gemma":0.001924554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0456344,"about_ca_topic_score_gemma":0.07190889,"domain_scores_codex":[0.9949249,0.001970651,0.0003843092,0.0005373341,0.001668843,0.0005139917],"domain_scores_gemma":[0.9279916,0.0515817,0.003967496,0.002438318,0.01034642,0.003674426],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.01668318,0.01843277,0.6542665,0.00100765,0.0008151436,0.0006649421,0.04841566,0.006375474,0.04521172,0.001369118,0.007633252,0.1991246],"study_design_scores_gemma":[0.0001912371,0.00673974,0.9722347,0.00006034479,0.0001311985,0.0001057876,0.007622588,0.004911627,0.005666104,0.0002218301,0.002036418,0.00007837884],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9967539,0.00002942571,0.0003222578,0.0000403794,0.00001708666,0.00009050826,0.0001697399,0.00002873285,0.002547882],"genre_scores_gemma":[0.9962952,0.00003298649,0.0007698198,0.00005027893,0.00001094983,0.0001121244,0.0004481974,0.00001467594,0.002265901],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.0456344,"threshold_uncertainty_score":0.09073752,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1748247609159025,"score_gpt":0.4753560976348649,"score_spread":0.3005313367189624,"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."}}