{"id":"W4394873790","doi":"10.1007/s00464-024-10807-w","title":"The performance of artificial intelligence large language model-linked chatbots in surgical decision-making for gastroesophageal reflux disease","year":2024,"lang":"en","type":"article","venue":"Surgical Endoscopy","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":24,"is_retracted":false,"has_abstract":false,"ca_institutions":"McMaster University","funders":"","keywords":"Perplexity; GERD; Guideline; Medicine; General surgery; Reflux; Medical emergency; Disease; Internal medicine; Language model; Computer science; Pathology; Artificial intelligence","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":[0.004656969,0.0008287912,0.0007452023,0.0006673431,0.0006072255,0.001495539,0.001060294,0.002326322,0.003467761],"category_scores_gemma":[0.02668609,0.0003038163,0.000409554,0.000390052,0.0005191072,0.001837078,0.001498021,0.001667163,0.001081377],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007830215,"about_ca_system_score_gemma":0.001235551,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006145756,"about_ca_topic_score_gemma":0.00480275,"domain_scores_codex":[0.9977849,0.001382438,0.0001456942,0.000290924,0.0002254538,0.0001706074],"domain_scores_gemma":[0.9708446,0.02582928,0.0006831379,0.0006923522,0.0009940309,0.0009565976],"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":[0.04760984,0.01308605,0.08031134,0.001621004,0.001218008,0.001501983,0.001948442,0.3842851,0.01662492,0.003724543,0.02225184,0.4258169],"study_design_scores_gemma":[0.0004062379,0.00205209,0.00700603,0.00004863689,0.0001578369,0.00009804479,0.0003568127,0.9821494,0.004064194,0.002798214,0.0008108143,0.00005169338],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9862188,0.0006849762,0.007661591,0.0007920043,0.0002592647,0.0000821616,0.0004974953,0.001342228,0.002461503],"genre_scores_gemma":[0.9929737,0.00008581365,0.005071231,0.0001894708,0.00004254404,0.00003407726,0.0006084849,0.00003255597,0.000962183],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.006145756,"threshold_uncertainty_score":0.0246287,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06467560335054845,"score_gpt":0.4351248248935671,"score_spread":0.3704492215430187,"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."}}