{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0207907,0.0001376728,0.002163409,0.00155267,0.00003317661,0.000007603385,0.0003982158,0.0003442436,0.0006190745],"category_scores_gemma":[0.03978215,0.00009324105,0.0003427751,0.0009662161,0.0003030913,0.00008235744,0.0001272193,0.001937351,0.000006612132],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001968318,"about_ca_system_score_gemma":0.007112765,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001447097,"about_ca_topic_score_gemma":0.00007435031,"domain_scores_codex":[0.9930688,0.0008248639,0.003484858,0.0002337614,0.002134919,0.0002527999],"domain_scores_gemma":[0.9820734,0.01459779,0.0008498213,0.0002542788,0.001816343,0.000408336],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"systematic_review","study_design_scores_codex":[0.00002556054,0.0002147408,0.0001994021,0.103267,0.00009277363,0.00006267162,0.00009003015,3.215219e-8,3.81435e-8,0.0004353088,0.005687533,0.8899249],"study_design_scores_gemma":[0.0000761677,0.0001114659,0.000009923788,0.8052717,0.0001447223,0.0001618226,0.0002065758,0.0000362612,4.897593e-7,0.0004255254,0.1935051,0.00005021547],"study_design_candidate":"systematic_review","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00002185178,0.986993,0.0005991248,0.01015109,0.0003862031,0.001026163,0.000006630029,0.00000283227,0.0008131653],"genre_scores_gemma":[0.0001217175,0.9976067,0.0001486515,0.0006502907,0.00115777,0.00009181498,0.00003527919,0.00001245847,0.0001753065],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8898747,"threshold_uncertainty_score":0.998516,"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."}}