{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T03:40:14Z","timestamp":1791430814193,"version":"4.3.3"},"reference-count":29,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T00:00:00Z","timestamp":1766016000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Public Health"],"abstract":"<jats:p>Early identification of trauma patients at risk of in-hospital death is essential for guiding time-critical resuscitation and operative strategies. We developed and evaluated a multi-model machine learning framework that integrates vital signs, and routine laboratory and blood-gas metrics indices obtained within 30\u202fmin of emergency department arrival to predict in-hospital mortality. This single-center retrospective study included 408 critically injured trauma patients treated at the Emergency Department of the Affiliated Kunshan Hospital of Jiangsu University (January 2020\u2013December 2021). We implemented multiple machine learning models [logistic regression, Random Forest, Gradient Boosting, XGBoost, LightGBM, and multilayer perceptron (MLP)], and constructed stacking and soft-voting ensembles. On the test set, single-model AUROC ranged from 0.743 to 0.927, with corresponding AUPRC spanning 0.438 to 0.904. The stacking ensemble achieved AUROC 0.9462 and AUPRC 0.8679; the voting ensemble achieved AUROC 0.9506 and AUPRC 0.8715. Permutation importance in the stacking model prioritized Injury Severity Score (ISS) (mean AUROC decrease 0.0360), base excess (BE) (0.0258), Glasgow Coma Scale (GCS) (0.0247), and pH (0.0153). In conclusion, an ensemble machine learning approach integrating early vital signs and laboratory data provides excellent discrimination and calibration for in-hospital mortality after severe trauma, with dominant contributions from ISS, GCS, and acid\u2013base variables. These findings support the feasibility of interpretable ensemble learning for early mortality risk stratification in severe trauma.<\/jats:p>","DOI":"10.3389\/fpubh.2025.1716910","type":"journal-article","created":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T06:43:10Z","timestamp":1766040190000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Early mortality prediction after severe trauma using ensemble machine learning: a single-center retrospective study"],"prefix":"10.3389","volume":"13","author":[{"given":"Lijing","family":"Ling","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohua","family":"Xia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hua","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shifang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuelan","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,12,18]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1136\/injuryprev-2015-041616","article-title":"The global burden of injury: incidence, mortality, disability-adjusted life years and time trends from the Global Burden of Disease study 2013","volume":"22","author":"Haagsma","year":"2016","journal-title":"Inj Prev"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"2314","DOI":"10.1016\/S0140-6736(24)01446-6","article-title":"The burden of diseases, injuries, and risk factors by state in the USA, 1990-2021: a systematic analysis for the Global Burden of Disease Study 2021","volume":"404","year":"2024","journal-title":"Lancet"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"1789","DOI":"10.1016\/S0140-6736(18)32279-7","article-title":"Global, regional, and national incidence, prevalence, and years lived with disability for 354 diseases and injuries for 195 countries and territories, 1990-2017: a systematic analysis for the Global Burden of Disease Study 2017","volume":"392","year":"2018","journal-title":"Lancet"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/S0140-6736(74)91639-0","article-title":"Assessment of coma and impaired consciousness. A practical scale","volume":"2","author":"Teasdale","year":"1974","journal-title":"Lancet"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"l1296","DOI":"10.1136\/bmj.l1296","article-title":"Glasgow coma scale explained","volume":"365","author":"Mehta","year":"2019","journal-title":"BMJ"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"844","DOI":"10.1016\/S1474-4422(14)70120-6","article-title":"The Glasgow Coma Scale at 40 years: standing the test of time","volume":"13","author":"Teasdale","year":"2014","journal-title":"Lancet Neurol"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1097\/00005373-197403000-00001","article-title":"The injury severity score: a method for describing patients with multiple injuries and evaluating emergency care","volume":"14","author":"Baker","year":"1974","journal-title":"J Trauma"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"440","DOI":"10.1016\/1047-2797(95)00059-3","article-title":"The injury severity score\u2014Importance and uses","volume":"5","author":"Linn","year":"1995","journal-title":"Ann Epidemiol"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1590\/s0104-11692008000200022","article-title":"Ten years of new injury severity score (NISS): is it a possible change?","volume":"16","author":"Nogueira Lde","year":"2008","journal-title":"Rev Lat Am Enfermagem"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1016\/S0196-0644(94)70279-9","article-title":"A comparison of the shock index and conventional vital signs to identify acute, critical illness in the emergency department","volume":"24","author":"Rady","year":"1994","journal-title":"Ann Emerg Med"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"1181","DOI":"10.1007\/s00134-021-06506-y","article-title":"Surviving sepsis campaign: international guidelines for management of sepsis and septic shock 2021","volume":"47","author":"Evans","year":"2021","journal-title":"Intensive Care Med"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"964","DOI":"10.1097\/00005373-199911000-00028","article-title":"The golden hour and the silver day: detection and correction of occult hypoperfusion within 24 hours improves outcome from major trauma","volume":"47","author":"Blow","year":"1999","journal-title":"J Trauma"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1007\/s001340051352","article-title":"Base excess and lactate as prognostic indicators for patients admitted to intensive care","volume":"27","author":"Smith","year":"2001","journal-title":"Intensive Care Med"},{"key":"ref14","first-page":"35","article-title":"Blood gas analyzers","volume":"1","author":"Kozlowski-Templin","year":"1995","journal-title":"Respir Care Clin N Am"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"R48","DOI":"10.1186\/cc12567","article-title":"Accuracy of blood-glucose measurements using glucose meters and arterial blood gas analyzers in critically ill adult patients: systematic review","volume":"17","author":"Inoue","year":"2013","journal-title":"Crit Care"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"8302","DOI":"10.1038\/s41598-024-58830-0","article-title":"Predicting the complexity and mortality of polytrauma patients with machine learning models","volume":"14","author":"Yu","year":"2024","journal-title":"Sci Rep"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"1073","DOI":"10.1007\/s00068-023-02423-5","article-title":"Machine learning in the prediction of massive transfusion in trauma: a retrospective analysis as a proof-of-concept","volume":"50","author":"Nikouline","year":"2024","journal-title":"Eur J Trauma Emerg Surg"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1111\/acem.12876","article-title":"Prediction of In-hospital Mortality in Emergency Department Patients With Sepsis: A Local Big Data-Driven","volume":"23","author":"Taylor","year":"2016","journal-title":"Mach Learn Approach Acad Emerg Med"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1290117","DOI":"10.3389\/fneur.2023.1290117","article-title":"Factor analysis based on SHapley Additive exPlanations for sepsis-associated encephalopathy in ICU mortality prediction using XGBoost - a retrospective study based on two large database","volume":"14","author":"Guo","year":"2023","journal-title":"Front Neurol"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"1367340","DOI":"10.3389\/fimmu.2024.1367340","article-title":"Creating machine learning models that interpretably link systemic inflammatory index, sex steroid hormones, and dietary antioxidants to identify gout using the SHAP (SHapley Additive exPlanations) method","volume":"15","author":"Cao","year":"2024","journal-title":"Front Immunol"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"229","DOI":"10.3390\/jimaging8090229","article-title":"Shapley-additive-explanations-based factor analysis for dengue severity prediction using machine learning","volume":"8","author":"Chowdhury","year":"2022","journal-title":"J Imaging"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"e939118","DOI":"10.12659\/MSM.939118","article-title":"Glasgow Coma Scale as an Indicator of Patient Prognosis: A Retrospective Study of 257 Patients with Heatstroke from 3 Medical Centers in Guangdong","volume":"29","author":"Chen","year":"2023","journal-title":"China Med Sci Monit"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1016\/j.jamcollsurg.2004.02.030","article-title":"Mortality prediction of head Abbreviated Injury Score and Glasgow Coma Scale: analysis of 7,764 head injuries","volume":"199","author":"Demetriades","year":"2004","journal-title":"J Am Coll Surg"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"825","DOI":"10.3390\/ijerph13080825","article-title":"Comparison of the ability to predict mortality between the injury severity score and the new injury severity score: a meta-analysis","volume":"13","author":"Deng","year":"2016","journal-title":"Int J Environ Res Public Health"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"e27753","DOI":"10.1097\/MD.0000000000027753","article-title":"Predicting outcomes after trauma: Prognostic model development based on admission features through machine learning","volume":"100","author":"Lee","year":"2021","journal-title":"Medicine (Baltimore)"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"815","DOI":"10.1097\/SHK.0000000000002516","article-title":"Predicting in-Hospital Mortality in Critical Orthopedic Trauma Patients with Sepsis Using Machine Learning Models","volume":"63","author":"Long","year":"2025","journal-title":"Shock"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"1851","DOI":"10.1016\/j.surg.2022.08.007","article-title":"Multidimensional machine learning models predicting outcomes after trauma","volume":"172","author":"Moris","year":"2022","journal-title":"Surgery"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"201","DOI":"10.20408\/jti.2024.0024","article-title":"Predicting 30-day mortality in severely injured elderly patients with trauma in Korea using machine learning algorithms: a retrospective study","volume":"37","author":"Han","year":"2024","journal-title":"J Trauma Inj"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"11690","DOI":"10.1038\/s41598-024-61739-3","article-title":"Machine learning models for predicting early hemorrhage progression in traumatic brain injury","volume":"14","author":"Lee","year":"2024","journal-title":"Sci Rep"}],"container-title":["Frontiers in Public Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2025.1716910\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T06:43:12Z","timestamp":1766040192000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2025.1716910\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,18]]},"references-count":29,"alternative-id":["10.3389\/fpubh.2025.1716910"],"URL":"https:\/\/doi.org\/10.3389\/fpubh.2025.1716910","relation":{},"ISSN":["2296-2565"],"issn-type":[{"value":"2296-2565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,18]]},"article-number":"1716910"}}