{"id":"W4399810434","doi":"10.1002/ohn.864","title":"ChatENT: Augmented Large Language Model for Expert Knowledge Retrieval in Otolaryngology–Head and Neck Surgery","year":2024,"lang":"en","type":"article","venue":"Otolaryngology","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":29,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Otorhinolaryngology; Popularity; Computer science; Specialty; Language model; Consistency (knowledge bases); Health care; Recall; Medicine; Artificial intelligence; Psychology; Pathology; Surgery","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"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":[0.001744997,0.000949749,0.0006036749,0.001059766,0.0004074195,0.001167926,0.001634596,0.001333345,0.004097354],"category_scores_gemma":[0.007406708,0.0003988513,0.001474453,0.0004895105,0.0003401898,0.00167328,0.001391618,0.001535835,0.001105779],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00105807,"about_ca_system_score_gemma":0.001606976,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01681682,"about_ca_topic_score_gemma":0.02180959,"domain_scores_codex":[0.9992557,0.0003322863,0.00006720376,0.00018652,0.0001094568,0.00004877782],"domain_scores_gemma":[0.9976544,0.001726558,0.0001005049,0.0001732829,0.0002598783,0.00008550944],"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":[0.001448938,0.0008998732,0.006000894,0.0008215734,0.0004560651,0.0007873765,0.0008534038,0.3388921,0.013301,0.003929368,0.0267304,0.6058791],"study_design_scores_gemma":[0.00006158123,0.0001649278,0.0007185932,0.00002812793,0.00006288588,0.00008304667,0.0000656846,0.9904065,0.002293023,0.002686102,0.003402896,0.00002669911],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.135294,0.001677941,0.823051,0.001507887,0.0003554832,0.001092387,0.003629781,0.02869066,0.004700815],"genre_scores_gemma":[0.5894808,0.0005416872,0.3945397,0.000981301,0.0001526151,0.001122709,0.00695188,0.0003687687,0.005860539],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01681682,"threshold_uncertainty_score":0.03343791,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1031967807500418,"score_gpt":0.4130537295793165,"score_spread":0.3098569488292747,"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."}}