{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T05:11:24Z","timestamp":1788757884788,"version":"build-2803163510"},"reference-count":22,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T00:00:00Z","timestamp":1788739200000},"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. Med."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aims to develop and validate machine learning (ML) models for predicting treatment failure in trauma patients using comprehensive clinical and laboratory variables, and to identify key prognostic features.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A retrospective cohort of 318 trauma patients was included. We included 44 characteristics, and the primary outcome was treatment failure at hospital discharge, defined as in-hospital death, an unimproved or worsened discharge status, discharge against medical advice or withdrawal of active treatment because of critical illness, or a GOS score of 1\u20133 in patients with concomitant traumatic brain injury. The dataset was randomly divided into a training set (70%) and a test set (30%). Features were selected via least absolute shrinkage and selection operator (LASSO) regression in the training set. 5 ML models\u2014Decision Tree (DT), Random Forest (RF), Support Vector Machine (SVM), k-Nearest Neighbors (KNN), and Extreme Gradient Boosting (XGBoost)\u2014were trained and evaluated. The optimal model was interpreted using SHapley Additive exPlanations (SHAP) analysis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>LASSO regression selected 13 candidate predictors for model development in the training set. The RF model demonstrated the best performance in the test set, with an AUC of 0.967 (95% CI: 0.936\u20130.997), sensitivity of 1.000, specificity of 0.855, and F1-score of 0.776. SHAP analysis identified Glasgow Coma Scale (GCS) score as the most influential predictor, followed by Multiple Organ Dysfunction Syndrome (MODS), Acute PHysiology and Chronic Health Evaluation (APACHE II) score, Injury Severity Score (ISS), and creatine kinase (CK). Higher APACHE II and ISS scores were positively associated with treatment failure, while higher GCS, absence of MODS and CK levels correlated with reduced risk.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Utilizing multiple trauma severity scores, laboratory parameters, and machine learning algorithms, we developed a predictive model to identify trauma patients at risk of treatment failure within the first 24\u2005h of admission. Among the algorithms evaluated, RF model demonstrated superior internal discriminative performance in our single-center cohort. SHAP interpretability analysis reveals the core prognostic value of GCS, MODS, APACHE II, ISS, and CK, providing a potential transparent auxiliary tool for clinical risk stratification. However, its generalization performance still needs multi center external validation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1919742","type":"journal-article","created":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T04:22:59Z","timestamp":1788754979000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Development and validation of an interpretable machine-learning model for predicting treatment failure in severe trauma patients"],"prefix":"10.3389","volume":"13","author":[{"given":"Qiang","family":"Shi","sequence":"first","affiliation":[{"name":"Department of Emergency, Suzhou Ninth People\u2019s Hospital, Suzhou Ninth Hospital Affiliated to Soochow University","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yun","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Emergency, Suzhou Ninth People\u2019s Hospital, Suzhou Ninth Hospital Affiliated to Soochow University","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiahui","family":"Shen","sequence":"additional","affiliation":[{"name":"Department of Emergency Intensive Care Unit, Suzhou Ninth People\u2019s Hospital, Suzhou Ninth Hospital Affiliated to Soochow University","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Yin","sequence":"additional","affiliation":[{"name":"Department of Emergency, Suzhou Ninth People\u2019s Hospital, Suzhou Ninth Hospital Affiliated to Soochow University","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenguo","family":"Qiao","sequence":"additional","affiliation":[{"name":"Department of Gastroenterology, Suzhou Ninth People\u2019s Hospital, Suzhou Ninth Hospital Affiliated to Soochow University","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xie","family":"Shen","sequence":"additional","affiliation":[{"name":"Department of Emergency, Suzhou Ninth People\u2019s Hospital, Suzhou Ninth Hospital Affiliated to Soochow University","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Emergency, Suzhou Ninth People\u2019s Hospital, Suzhou Ninth Hospital Affiliated to Soochow University","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deli","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Emergency, Suzhou Ninth People\u2019s Hospital, Suzhou Ninth Hospital Affiliated to Soochow University","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Teng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Emergency, Suzhou Ninth People\u2019s Hospital, Suzhou Ninth Hospital Affiliated to Soochow University","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengzhi","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Emergency, Suzhou Ninth People\u2019s Hospital, Suzhou Ninth Hospital Affiliated to Soochow University","place":["Suzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,7]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"e65778","DOI":"10.7759\/cureus.65778","article-title":"Comparative prognostic value of the national institutes of health stroke scale (NIHSS) and the Glasgow coma scale (GCS) in supratentorial and infratentorial stroke patients in western India","volume":"16","author":"Padwale","year":"2024","journal-title":"Cureus"},{"key":"B2","doi-asserted-by":"publisher","first-page":"737","DOI":"10.3390\/ijms22020737","article-title":"Trauma, a matter of the heart-molecular mechanism of post-traumatic cardiac dysfunction","volume":"22","author":"Weber","year":"2021","journal-title":"Int J Mol Sci"},{"key":"B3","doi-asserted-by":"publisher","first-page":"804","DOI":"10.1186\/s40001-025-03100-6","article-title":"The predictive value of the lactate\/albumin ratio combined with APACHE II and injury severity score for short-term prognosis in patients with polytrauma","volume":"30","author":"Zhao","year":"2025","journal-title":"Eur J Med Res"},{"key":"B4","doi-asserted-by":"publisher","first-page":"737","DOI":"10.14744\/tjtes.2024.15003","article-title":"Prognostic indicators in patients with isolated thoracic trauma: a retrospective cross-sectional study","volume":"30","author":"Yaz\u0131c\u0131","year":"2024","journal-title":"Ulus Travma Acil Cerrahi Derg\/Turk J Trauma Emerg Surg"},{"key":"B5","doi-asserted-by":"publisher","first-page":"107739","DOI":"10.1016\/j.biotechadv.2021.107739","article-title":"Using machine learning approaches for multi-omics data analysis: a review","volume":"49","author":"Reel","year":"2021","journal-title":"Biotechnol Adv"},{"key":"B6","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1272\/jnms.JNMS.2023_90-206","article-title":"Development of a machine learning model to predict cardiac arrest during transport of trauma patients","volume":"90","author":"Kitano","year":"2023","journal-title":"J Nippon Med Sch"},{"key":"B7","doi-asserted-by":"publisher","first-page":"e0276624","DOI":"10.1371\/journal.pone.0276624","article-title":"ICD-10 based machine learning models outperform the trauma and injury severity score (TRISS) in survival prediction","volume":"17","author":"Tran","year":"2022","journal-title":"PLoS One"},{"key":"B8","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1016\/j.jss.2023.12.016","article-title":"Identifying age-specific risk factors for poor outcomes after trauma with machine learning","volume":"296","author":"Kregel","year":"2024","journal-title":"J Surg Res"},{"key":"B9","doi-asserted-by":"publisher","first-page":"e1300","DOI":"10.1016\/j.wneu.2023.04.121","article-title":"Correlation between clinical findings at admission and Glasgow outcome scale score in children with traumatic brain injury","volume":"175","author":"Rezakhah","year":"2023","journal-title":"World Neurosurg"},{"key":"B10","doi-asserted-by":"publisher","first-page":"105948","DOI":"10.1016\/j.ijsu.2021.105948","article-title":"Evaluation and analysis of incidence and risk factors of lower extremity venous thrombosis after urologic surgeries: a prospective two-center cohort study using LASSO-logistic regression","volume":"89","author":"Tang","year":"2021","journal-title":"Int J Surg (London, England)"},{"key":"B11","doi-asserted-by":"publisher","first-page":"118569","DOI":"10.1016\/j.ecoenv.2025.118569","article-title":"Interpretable machine learning insights into the association between PFAS exposure and diabetes mellitus","volume":"302","author":"Wang","year":"2025","journal-title":"Ecotoxicol Environ Saf"},{"key":"B12","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1007\/s10916-025-02211-1","article-title":"SHAP-Driven Feature analysis approach for epileptic seizure prediction","volume":"49","author":"Hasan","year":"2025","journal-title":"J Med Syst"},{"key":"B13","doi-asserted-by":"publisher","first-page":"e866","DOI":"10.1016\/j.wneu.2023.12.064","article-title":"Development of a novel neurological score combining GCS and FOUR scales for assessment of neurosurgical patients with traumatic brain injury: GCS-FOUR scale","volume":"182","author":"Ansari","year":"2024","journal-title":"World Neurosurg"},{"key":"B14","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1016\/j.injury.2022.09.035","article-title":"Glasgow Coma scale compared to other trauma scores in discriminating in-hospital mortality of traumatic brain injury patients admitted to urban Indian hospitals: a multicentre prospective cohort study","volume":"54","author":"Basak","year":"2023","journal-title":"Injury"},{"key":"B15","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1186\/s12887-023-04437-9","article-title":"Development and validation of a pediatric model predicting trauma-related mortality","volume":"23","author":"Evans","year":"2023","journal-title":"BMC Pediatr"},{"key":"B16","doi-asserted-by":"publisher","first-page":"959","DOI":"10.1016\/j.injury.2021.11.026","article-title":"Elevated monocyte distribution width in trauma: an early cellular biomarker of organ dysfunction","volume":"53","author":"Marcos-Morales","year":"2022","journal-title":"Injury"},{"key":"B17","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1186\/s40001-022-00822-9","article-title":"Evaluation of mortality prediction using SOFA and APACHE IV tools in trauma and non-trauma patients admitted to the ICU","volume":"27","author":"Karami Niaz","year":"2022","journal-title":"Eur J Med Res"},{"key":"B18","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1186\/s12876-025-03723-3","article-title":"Explainable machine learning model for predicting acute pancreatitis mortality in the intensive care unit","volume":"25","author":"Jiang","year":"2025","journal-title":"BMC Gastroenterol"},{"key":"B19","doi-asserted-by":"publisher","first-page":"108589","DOI":"10.1016\/j.cmpb.2025.108589","article-title":"Machine learning-based 28-day mortality prediction model for elderly neurocritically ill patients","volume":"260","author":"Yuan","year":"2025","journal-title":"Comput Methods Programs Biomed"},{"key":"B20","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1097\/CM9.0000000000002773","article-title":"Association of creatine kinase with Alzheimer\u2019s disease pathology: a cross-sectional study","volume":"137","author":"Wang","year":"2024","journal-title":"Chin Med J"},{"key":"B21","doi-asserted-by":"publisher","first-page":"421","DOI":"10.1038\/s41574-020-0365-5","article-title":"Creatine metabolism: energy homeostasis, immunity and cancer biology","volume":"16","author":"Kazak","year":"2020","journal-title":"Na Rev Endocrinol"},{"key":"B22","doi-asserted-by":"publisher","first-page":"156532","DOI":"10.1016\/j.phymed.2025.156532","article-title":"Ligustilide covalently binds to Cys254 of the creatine kinase, M-type protein, ameliorating acute myocardial ischemia by enhancing the creatine phosphate level","volume":"139","author":"Zhang","year":"2025","journal-title":"Phytomedicine"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1919742\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T04:22:59Z","timestamp":1788754979000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1919742\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,7]]},"references-count":22,"alternative-id":["10.3389\/fmed.2026.1919742"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1919742","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,7]]},"article-number":"1919742"}}