{"id":"W4412027990","doi":"10.1177/03000605251347556","title":"Clinical applications of large language models in medicine and surgery: A scoping review","year":2025,"lang":"en","type":"review","venue":"Journal of International Medical Research","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"Impact; McMaster University","funders":"","keywords":"Medicine; CINAHL; Data extraction; Protocol (science); MEDLINE; Systematic review; Medical physics; Sample size determination; Clinical study design; Clinical trial; Computer science; Alternative medicine; Pathology; Psychological intervention; Statistics","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":[0.08935012,0.002887693,0.006396919,0.02130234,0.001366933,0.008899653,0.004319638,0.003302518,0.006630903],"category_scores_gemma":[0.2440627,0.001891163,0.01184743,0.01710045,0.002388354,0.009581579,0.005394041,0.003173278,0.0009822124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008389763,"about_ca_system_score_gemma":0.0239914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.008423386,"about_ca_topic_score_gemma":0.01538932,"domain_scores_codex":[0.9360154,0.03817509,0.01454797,0.002184001,0.008334235,0.0007432754],"domain_scores_gemma":[0.6904562,0.2679238,0.01771134,0.006027505,0.01725309,0.0006280316],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0003186374,0.0001334097,0.002035813,0.6125714,0.007117667,0.0002038147,0.001600493,0.002194295,0.0002994963,0.006287744,0.006538045,0.3606993],"study_design_scores_gemma":[0.0001188027,0.0002249656,0.001755585,0.9283816,0.01399615,0.0002936741,0.0009375123,0.001250476,0.0003340627,0.005468765,0.04713935,0.00009900643],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.001150083,0.987349,0.005637259,0.002102803,0.00033213,0.00124471,0.0004358955,0.00006378452,0.001684348],"genre_scores_gemma":[0.02424771,0.9529212,0.01617318,0.001570146,0.0003202556,0.003781361,0.0006875372,0.00005784048,0.0002409216],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.08935012,"threshold_uncertainty_score":0.4725342,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6605177682834921,"score_gpt":0.7218189038617205,"score_spread":0.06130113557822847,"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."}}