{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006434511,0.0001889209,0.0004501316,0.0004275332,0.00008984685,0.00002175569,0.00006733887,0.0003437884,0.0000934425],"category_scores_gemma":[0.0004005059,0.0001763036,0.0001111067,0.0003335278,0.00009130959,0.0001301877,0.00004692377,0.0003248107,0.0000680483],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001296692,"about_ca_system_score_gemma":0.0003748517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002310801,"about_ca_topic_score_gemma":0.0005568176,"domain_scores_codex":[0.9982765,0.00008523928,0.000496996,0.0004923878,0.00008681349,0.000562102],"domain_scores_gemma":[0.9989189,0.0005333894,0.00004477192,0.0002468718,0.00009043681,0.0001656559],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.007430557,0.004001813,0.5886183,0.01004128,0.0005656903,0.001989821,0.1442959,0.00004076568,0.07064351,0.02460997,0.04914294,0.09861936],"study_design_scores_gemma":[0.001002758,0.001050162,0.1021858,0.001955256,0.0001409755,0.0009890071,0.003096369,0.8403124,0.01731791,0.002899715,0.02818405,0.0008656233],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9777859,0.01470072,0.001953459,0.003236709,0.0009141754,0.0008624136,0.00002412928,0.0001303978,0.000392144],"genre_scores_gemma":[0.9956388,0.0007107996,0.000450085,0.001169273,0.0003978086,0.0001872617,0.0001774951,0.00004360842,0.001224878],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8402716,"threshold_uncertainty_score":0.7189452,"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."}}