{"id":"W4409235391","doi":"10.1038/s44222-025-00279-5","title":"Application of large language models in medicine","year":2025,"lang":"en","type":"article","venue":"Nature Reviews Bioengineering","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University; University of Waterloo","funders":"","keywords":"Computer science; Linguistics; Philosophy","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":[0.004589696,0.0009893416,0.001284818,0.001749884,0.0005497705,0.002408851,0.001177521,0.001233507,0.004458172],"category_scores_gemma":[0.02330282,0.0006172428,0.001515863,0.001376245,0.000806296,0.002913878,0.001740158,0.002531962,0.00211531],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009150548,"about_ca_system_score_gemma":0.00146387,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003867085,"about_ca_topic_score_gemma":0.004141885,"domain_scores_codex":[0.9975109,0.001724507,0.00009484226,0.0002325386,0.0003844472,0.00005269421],"domain_scores_gemma":[0.9823472,0.01545918,0.0003725178,0.0009100813,0.0007375371,0.0001734785],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005840316,0.0004300338,0.006707997,0.001312651,0.00125814,0.0008520973,0.0004332644,0.3577255,0.009708426,0.08066437,0.03497654,0.505347],"study_design_scores_gemma":[0.00005141593,0.0000571816,0.0008113065,0.00009588004,0.0001282581,0.0001885876,0.00005773982,0.828288,0.001976009,0.1568007,0.01150461,0.0000403522],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"review","genre_scores_codex":[0.01871766,0.01062716,0.9501792,0.008751282,0.0008135163,0.0001160832,0.001882905,0.0034666,0.005445609],"genre_scores_gemma":[0.6224418,0.01463157,0.3416322,0.003866049,0.002276627,0.0005482412,0.004872716,0.001210196,0.008520573],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.004589696,"threshold_uncertainty_score":0.02427292,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01100618048205574,"score_gpt":0.3404888946772798,"score_spread":0.329482714195224,"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."}}