{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007549814,0.0001013259,0.0003090397,0.0002566453,0.00001445789,0.00000502147,0.0004911365,0.0001283154,0.000002210483],"category_scores_gemma":[0.0002050676,0.00008206673,0.00003736111,0.00104481,0.000007394829,0.000103047,0.00009965681,0.0005086683,0.000002504756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004484051,"about_ca_system_score_gemma":0.0000174552,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005555853,"about_ca_topic_score_gemma":0.00001977031,"domain_scores_codex":[0.9991004,0.00005426023,0.0003479741,0.000219708,0.000117195,0.000160497],"domain_scores_gemma":[0.9992976,0.00006354148,0.0000806175,0.0004964363,0.00003388303,0.00002790875],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002093264,0.00003324689,0.002219756,0.003117116,0.00000924584,0.000004614016,0.001249587,0.009136838,0.002876135,0.5923747,0.0005738132,0.3884029],"study_design_scores_gemma":[0.0002030207,0.00001369907,0.00206022,0.00097833,0.000004008587,0.000001952167,0.00001217441,0.9256313,0.000228771,0.0007578694,0.07000917,0.00009946468],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005366433,0.1369772,0.859134,0.001651232,0.0001823814,0.0003419036,8.437863e-7,0.00008036438,0.001095492],"genre_scores_gemma":[0.9647379,0.002275668,0.03234868,0.0004771768,0.00004811673,0.00004677055,0.000005875757,0.000006839178,0.00005296162],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9642013,"threshold_uncertainty_score":0.3346584,"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."}}