{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T04:58:06Z","timestamp":1783573086228,"version":"3.55.0"},"reference-count":44,"publisher":"SAGE Publications","issue":"4","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["82374069"],"award-info":[{"award-number":["82374069"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Health Informatics J"],"published-print":{"date-parts":[[2025,10]]},"abstract":"<jats:p>We develop and validate a clinical guideline-integrated LLM for enhanced sepsis mortality prediction. Using MIMIC-IV data from 24,237 ICU sepsis patients, we fine-tuned a large language model with Low-Rank Adaptation, embedding clinical guidelines into the training process. The model\u2019s predictive performance was evaluated using accuracy, F1-score, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). Ablation studies assessed the specific contributions of clinical guideline integration. The guideline-enhanced fine-tuned LLM demonstrated moderately higher performance across all evaluation metrics including predictive accuracy (0.819), F1-score (0.815), sensitivity (0.815), specificity (0.822), and AUC (0.852) in predicting mortality risk for septic patients compared to traditional machine learning (highest accuracy: 0.774, AUC: 0.850) and deep learning methods (highest accuracy: 0.762, AUC: 0.841). Ablation experiments demonstrated that explicit integration of clinical guideline knowledge substantially improved performance over both direct prompting (accuracy: 0.709, AUC: 0.706) and fine-tuning without clinical guidelines (accuracy: 0.786, AUC: 0.801). These findings demonstrate that\u00a0incorporating clinical guidelines into the fine-tuning of large language models outperforms both traditional and deep learning baselines across multiple metrics in sepsis mortality prediction, highlighting the value of explicit domain knowledge integration for clinical AI\u2019s robustness.<\/jats:p>","DOI":"10.1177\/14604582251387649","type":"journal-article","created":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T11:29:51Z","timestamp":1762428591000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":3,"title":["Integrating clinical guidelines with large language models for improved sepsis mortality prediction"],"prefix":"10.1177","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-6369-1497","authenticated-orcid":false,"given":"Zhen","family":"Zhao","sequence":"first","affiliation":[{"name":"Department of Emergency Medicine, Beijing Friendship Hospital affiliated Capital Medical University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"An","sequence":"additional","affiliation":[{"name":"Institute of Ethnology and Anthropology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianpeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, Beijing Friendship Hospital affiliated Capital Medical University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruiyi","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, Beijing Friendship Hospital affiliated Capital Medical University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zihao","family":"Fan","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, Beijing Friendship Hospital affiliated Capital Medical University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoxing","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, Beijing Friendship Hospital affiliated Capital Medical University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2025,11,6]]},"reference":[{"key":"e_1_3_6_2_2","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2016.0287"},{"key":"e_1_3_6_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(19)32989-7"},{"key":"e_1_3_6_4_2","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2018.7571"},{"key":"e_1_3_6_5_2","volume-title":"National inpatient hospital costs: the Most expensive conditions by payer, 2017. Healthcare cost and utilization project (HCUP) statistical briefs","author":"Liang L","year":"2006","unstructured":"Liang L, Moore B, Soni A. National inpatient hospital costs: the Most expensive conditions by payer, 2017. Healthcare cost and utilization project (HCUP) statistical briefs. Agency for Healthcare Research and Quality (US), 2006."},{"key":"e_1_3_6_6_2","doi-asserted-by":"publisher","DOI":"10.1097\/CCM.0000000000005337"},{"key":"e_1_3_6_7_2","doi-asserted-by":"publisher","DOI":"10.1097\/MS9.0000000000001744"},{"key":"e_1_3_6_8_2","doi-asserted-by":"publisher","DOI":"10.1097\/MS9.0000000000000696"},{"key":"e_1_3_6_9_2","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2020.00445"},{"key":"e_1_3_6_10_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0245157"},{"key":"e_1_3_6_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2021.106040"},{"key":"e_1_3_6_12_2","doi-asserted-by":"publisher","DOI":"10.1097\/CCM.0000000000002936"},{"key":"e_1_3_6_13_2","doi-asserted-by":"publisher","DOI":"10.1093\/jamiaopen\/ooac080"},{"key":"e_1_3_6_14_2","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/9263391"},{"key":"e_1_3_6_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2022.106874"},{"key":"e_1_3_6_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2020.101820"},{"key":"e_1_3_6_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/s12194-017-0406-5"},{"key":"e_1_3_6_18_2","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(23)00177-2"},{"key":"e_1_3_6_19_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00879-8"},{"key":"e_1_3_6_20_2","doi-asserted-by":"publisher","DOI":"10.2196\/56532"},{"key":"e_1_3_6_21_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13054-023-04393-x"},{"key":"e_1_3_6_22_2","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare11060887"},{"key":"e_1_3_6_23_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40663-9"},{"key":"e_1_3_6_24_2","doi-asserted-by":"publisher","DOI":"10.1111\/jocn.17061"},{"key":"e_1_3_6_25_2","volume-title":"MIMIC-IV","author":"Johnson A","year":"2024","unstructured":"Johnson A, Bulgarelli L, Pollard T, et al. MIMIC-IV. PhysioNet, 2024. version 3.1. https:\/\/physionet.org\/content\/mimiciv"},{"key":"e_1_3_6_26_2","doi-asserted-by":"publisher","DOI":"10.1002\/hsr2.70727"},{"key":"e_1_3_6_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcrc.2024.154889"},{"key":"e_1_3_6_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/s44197-025-00386-x"},{"key":"e_1_3_6_29_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-022-01899-x"},{"key":"e_1_3_6_30_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12873-022-00582-z"},{"key":"e_1_3_6_31_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12967-020-02620-5"},{"key":"e_1_3_6_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11255-023-03646-6"},{"key":"e_1_3_6_33_2","doi-asserted-by":"publisher","DOI":"10.2196\/29982"},{"key":"e_1_3_6_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2020.104312"},{"key":"e_1_3_6_35_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-023-02138-6"},{"key":"e_1_3_6_36_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jinf.2023.07.006"},{"key":"e_1_3_6_37_2","doi-asserted-by":"publisher","DOI":"10.1056\/EVIDstat2300128"},{"key":"e_1_3_6_38_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-024-18378-7"},{"key":"e_1_3_6_39_2","doi-asserted-by":"publisher","DOI":"10.1007\/s13755-022-00183-x"},{"key":"e_1_3_6_40_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-20910-4"},{"key":"e_1_3_6_41_2","doi-asserted-by":"publisher","DOI":"10.1111\/liv.15974"},{"key":"e_1_3_6_42_2","first-page":"191","article-title":"A review of challenges and opportunities in machine learning for health","volume":"2020","author":"Ghassemi M","year":"2020","unstructured":"Ghassemi M, Naumann T, Schulam P, et al. A review of challenges and opportunities in machine learning for health. AMIA Jt Summits Transl Sci Proc 2020; 2020: 191\u2013200.","journal-title":"AMIA Jt Summits Transl Sci Proc"},{"key":"e_1_3_6_43_2","doi-asserted-by":"publisher","DOI":"10.2196\/37685"},{"key":"e_1_3_6_44_2","doi-asserted-by":"publisher","DOI":"10.1002\/brb3.2742"},{"key":"e_1_3_6_45_2","doi-asserted-by":"publisher","DOI":"10.1111\/ene.70073"}],"container-title":["Health Informatics Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/14604582251387649","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/14604582251387649","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/14604582251387649","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T22:29:02Z","timestamp":1777501742000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/14604582251387649"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":44,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["10.1177\/14604582251387649"],"URL":"https:\/\/doi.org\/10.1177\/14604582251387649","relation":{},"ISSN":["1460-4582","1741-2811"],"issn-type":[{"value":"1460-4582","type":"print"},{"value":"1741-2811","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]},"article-number":"14604582251387649"}}