{"id":"W4413434333","doi":"10.1038/s41575-025-01108-1","title":"Large language models for clinical decision support in gastroenterology and hepatology","year":2025,"lang":"en","type":"review","venue":"Nature Reviews Gastroenterology & Hepatology","topic":"Machine Learning in Healthcare","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"ca_institutions":"University Health Network","funders":"","keywords":"Medicine; Hepatology; Internal medicine; Gastroenterology; MEDLINE; Intensive care medicine","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":["metaepi_narrow","research_integrity"],"consensus_categories":["metaepi_narrow","research_integrity"],"category_scores_codex":[0.005820182,0.001428323,0.009952124,0.001615464,0.0001863199,0.00005747146,0.003321606,0.004493944,0.0000371294],"category_scores_gemma":[0.00221425,0.001207788,0.001564615,0.0006651314,0.0003582117,0.0002774377,0.002262681,0.006398079,0.00004372501],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002872606,"about_ca_system_score_gemma":0.0007199623,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002493142,"about_ca_topic_score_gemma":0.002071435,"domain_scores_codex":[0.9816577,0.007651547,0.004659562,0.003315162,0.0002669118,0.002449045],"domain_scores_gemma":[0.9914159,0.003527973,0.001991756,0.002447919,0.0001991115,0.0004173419],"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":[0.0002745987,0.0003015249,0.04052842,0.01901634,0.0001840128,0.0004288501,0.0001111234,0.000001149197,2.157671e-8,0.006737312,0.01308195,0.9193347],"study_design_scores_gemma":[0.002100523,0.001689635,0.0001571734,0.003956031,0.0004092594,0.00242497,0.000005294865,0.003198839,1.748301e-8,0.001159555,0.9844888,0.0004098593],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0001425629,0.8845426,0.1064538,0.001436362,0.003300948,0.003742501,0.0001472307,0.0001694394,0.0000646118],"genre_scores_gemma":[0.0001750235,0.9571176,0.03012183,0.01038915,0.0002376651,0.001430123,0.0003646156,0.00008303866,0.00008100641],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9714069,"threshold_uncertainty_score":0.9998467,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04297474469545391,"score_gpt":0.4341969994327131,"score_spread":0.3912222547372592,"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."}}