{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T09:51:23Z","timestamp":1774864283288,"version":"3.50.1"},"reference-count":24,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T00:00:00Z","timestamp":1767571200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["clinicalkey.com","clinicalkey.com.au","clinicalkey.es","clinicalkey.fr","clinicalkey.jp","elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["International Journal of Medical Informatics"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1016\/j.ijmedinf.2026.106268","type":"journal-article","created":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T16:14:03Z","timestamp":1767629643000},"page":"106268","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"special_numbering":"C","title":["Predicting emergency mortality risk in traumatic brain injury: comparative analysis of machine learning and large language model GPT-5"],"prefix":"10.1016","volume":"209","author":[{"given":"Kuan-Chi","family":"Tu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yung-De","family":"Kuo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4239-4267","authenticated-orcid":false,"given":"Tee-Tau Eric","family":"Nyam","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu-Shan","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0608-5865","authenticated-orcid":false,"given":"Mei-I","family":"Sung","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6698-0273","authenticated-orcid":false,"given":"Chung-Feng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ching-Lung","family":"Kuo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.ijmedinf.2026.106268_b0005","doi-asserted-by":"crossref","first-page":"1080","DOI":"10.3171\/2017.10.JNS17352","article-title":"Estimating the global incidence of traumatic brain injury","volume":"130","author":"Dewan","year":"2019","journal-title":"J. Neurosurg."},{"key":"10.1016\/j.ijmedinf.2026.106268_b0010","doi-asserted-by":"crossref","first-page":"987","DOI":"10.1016\/S1474-4422(17)30371-X","article-title":"Traumatic brain injury: integrated approaches to improve prevention, clinical care, and research","volume":"16","author":"Maas","year":"2017","journal-title":"Lancet Neurol."},{"key":"10.1016\/j.ijmedinf.2026.106268_b0015","first-page":"e1","article-title":"Advances in neurocritical care and implications for traumatic brain injury outcomes","volume":"47","author":"Robertson","year":"2019","journal-title":"Crit. Care Med."},{"key":"10.1016\/j.ijmedinf.2026.106268_b0020","doi-asserted-by":"crossref","first-page":"612","DOI":"10.3390\/brainsci12050612","article-title":"A computer-assisted system for early mortality risk prediction in patients with traumatic brain injury using artificial intelligence algorithms in emergency room triage","volume":"12","author":"Tu","year":"2022","journal-title":"Brain Sci."},{"key":"10.1016\/j.ijmedinf.2026.106268_b0025","doi-asserted-by":"crossref","first-page":"3016","DOI":"10.3390\/diagnostics13183016","article-title":"Machine learning algorithm predicts mortality risk in intensive care unit for patients with traumatic brain injury","volume":"13","author":"Tu","year":"2023","journal-title":"Diagnostics (Basel)"},{"key":"10.1016\/j.ijmedinf.2026.106268_b0030","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1007\/s12028-016-0326-y","article-title":"FOUR score predicts early outcome in patients after traumatic brain injury","volume":"26","author":"Nyam","year":"2017","journal-title":"Neurocrit. Care"},{"key":"10.1016\/j.ijmedinf.2026.106268_b0035","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1023\/A:1022627411411","article-title":"Support-vector networks","volume":"20","author":"Cortes","year":"1995","journal-title":"Mach. Learn."},{"key":"10.1016\/j.ijmedinf.2026.106268_b0040","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach. Learn."},{"key":"10.1016\/j.ijmedinf.2026.106268_b0045","doi-asserted-by":"crossref","first-page":"183","DOI":"10.1016\/0925-2312(91)90023-5","article-title":"Multilayer perceptrons for classification and regression","volume":"2","author":"Murtagh","year":"1991","journal-title":"Neurocomputing"},{"key":"10.1016\/j.ijmedinf.2026.106268_b0050","series-title":"LightGBM: a highly efficient gradient boosting decision tree","author":"Ke","year":"2017"},{"key":"10.1016\/j.ijmedinf.2026.106268_b0055","first-page":"62","article-title":"Prediction of in-hospital mortality in patients with post-traumatic brain injury using National Trauma Registry and machine learning approach","volume":"28","author":"Kuo","year":"2020","journal-title":"Scand. J. Trauma Resusc. Emerg. Med."},{"key":"10.1016\/j.ijmedinf.2026.106268_b0060","doi-asserted-by":"crossref","first-page":"e125","DOI":"10.1016\/j.wneu.2022.06.130","article-title":"A machine learning-based prognostic model for the prediction of early death after traumatic brain injury: comparison with the CRASH model","volume":"166","author":"Lee","year":"2022","journal-title":"World Neurosurg."},{"key":"10.1016\/j.ijmedinf.2026.106268_b0065","doi-asserted-by":"crossref","first-page":"1376","DOI":"10.1089\/neu.2022.0280","article-title":"Prediction of mortality among patients with isolated traumatic brain injury using machine learning models in Asian countries: an international multi-center cohort study","volume":"40","author":"Song","year":"2023","journal-title":"J. Neurotrauma"},{"key":"10.1016\/j.ijmedinf.2026.106268_b0070","first-page":"11287","article-title":"Comparison of machine learning models to predict long-term outcomes after severe traumatic brain injury","volume":"13","author":"Jang","year":"2023","journal-title":"Sci. Rep."},{"key":"10.1016\/j.ijmedinf.2026.106268_b0075","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1186\/s12911-025-02944-6","article-title":"The role of explainable artificial intelligence in disease prediction: a systematic literature review and future research directions","volume":"25","author":"Alkhanbouli","year":"2025","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"10.1016\/j.ijmedinf.2026.106268_b0080","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","article-title":"Large language models encode clinical knowledge","volume":"620","author":"Singhal","year":"2023","journal-title":"Nature"},{"key":"10.1016\/j.ijmedinf.2026.106268_b0085","doi-asserted-by":"crossref","unstructured":"O.B. Shoham, N. Rappoport, CPLLM: clinical prediction with large language models, arXiv Preprint arXiv:2309.11295 (2023).","DOI":"10.1371\/journal.pdig.0000680"},{"key":"10.1016\/j.ijmedinf.2026.106268_b0090","doi-asserted-by":"crossref","first-page":"928","DOI":"10.1001\/jamasurg.2024.1621","article-title":"Large language model capabilities in perioperative risk prediction and prognostication","volume":"159","author":"Chung","year":"2024","journal-title":"JAMA Surg."},{"key":"10.1016\/j.ijmedinf.2026.106268_b0095","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1007\/s41666-025-00190-z","article-title":"Adapting generative large language models for information extraction from unstructured electronic health records in residential aged care: a comparative analysis of training approaches","volume":"9","author":"Vithanage","year":"2025","journal-title":"J. Healthc. Inform. Res."},{"key":"10.1016\/j.ijmedinf.2026.106268_b0100","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1038\/s41746-025-01689-w","article-title":"Development and prospective implementation of a large language model-based system for early sepsis prediction","volume":"8","author":"Shashikumar","year":"2025","journal-title":"NPJ Digit. Med."},{"key":"10.1016\/j.ijmedinf.2026.106268_b0105","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1007\/978-3-031-95838-0_7","article-title":"Comparative evaluation of clinical large language models and machine learning to predict antimicrobial resistance in hospital-onset sepsis","volume":"157","author":"Cohen","year":"2025","journal-title":"Artif. Intell. Med."},{"key":"10.1016\/j.ijmedinf.2026.106268_b0110","article-title":"Large language models are less effective at clinical prediction tasks than locally trained machine learning models","volume":"145","author":"Brown","year":"2025","journal-title":"J. Biomed. Inform."},{"issue":"1","key":"10.1016\/j.ijmedinf.2026.106268_b0115","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1038\/s41746-022-00742-2","article-title":"A large language model for electronic health records","volume":"5","author":"Yang","year":"2022","journal-title":"NPJ Digit Med."},{"key":"10.1016\/j.ijmedinf.2026.106268_b0120","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Adv. Neural Inf. Proces. Syst."}],"container-title":["International Journal of Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1386505626000080?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1386505626000080?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T08:52:17Z","timestamp":1774860737000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1386505626000080"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":24,"alternative-id":["S1386505626000080"],"URL":"https:\/\/doi.org\/10.1016\/j.ijmedinf.2026.106268","relation":{},"ISSN":["1386-5056"],"issn-type":[{"value":"1386-5056","type":"print"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Predicting emergency mortality risk in traumatic brain injury: comparative analysis of machine learning and large language model GPT-5","name":"articletitle","label":"Article Title"},{"value":"International Journal of Medical Informatics","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ijmedinf.2026.106268","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"106268"}}