{"id":"W4407237982","doi":"10.1016/j.bja.2025.01.001","title":"A comparison of large language model-generated and published perioperative neurocognitive disorder recommendations: a cross-sectional web-based analysis","year":2025,"lang":"en","type":"article","venue":"British Journal of Anaesthesia","topic":"Intensive Care Unit Cognitive Disorders","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Institute of General Medical Sciences; National Institutes of Health","keywords":"Neurocognitive; Cross-sectional study; Psychology; Medicine; Clinical psychology; Psychiatry; Cognition; Pathology","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004687667,0.0001720876,0.0007038918,0.0009078353,0.0001809342,0.0001631348,0.000104596,0.0001129144,0.0001922301],"category_scores_gemma":[0.002991476,0.0001846594,0.0003371578,0.00118506,0.0002081937,0.0002705714,0.00002856917,0.0004752082,7.733206e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000657615,"about_ca_system_score_gemma":0.0005221735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000905927,"about_ca_topic_score_gemma":0.0003695021,"domain_scores_codex":[0.9982057,0.0002243623,0.0007921848,0.0002521807,0.0003119057,0.0002136434],"domain_scores_gemma":[0.9888718,0.0001163258,0.0004083699,0.0001095119,0.01038391,0.0001100578],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0008999167,0.001047188,0.9779803,0.0000805696,0.001748805,0.0002832636,0.000917431,0.001442375,0.001594666,0.0002065519,0.002733445,0.0110655],"study_design_scores_gemma":[0.008090761,0.0007930057,0.8823886,0.0005738168,0.001550848,0.0002481608,0.008801678,0.09498584,0.001603994,0.00004718882,0.0006534913,0.0002626216],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9834478,0.002059842,0.0114704,0.001704689,0.00005835916,0.0002725571,0.0001480334,0.00001594818,0.0008223788],"genre_scores_gemma":[0.9934155,0.0001758185,0.001283718,0.004641903,0.00002282818,0.0000116556,0.0002076642,0.00001824824,0.0002226101],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09559169,"threshold_uncertainty_score":0.753019,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0152825022894158,"score_gpt":0.3449879412991688,"score_spread":0.329705439009753,"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."}}