{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T05:00:04Z","timestamp":1785214804213,"version":"3.55.0"},"reference-count":25,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T00:00:00Z","timestamp":1785196800000},"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. Neurol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Lower extremity deep vein thrombosis (LEDVT) is a common and clinically important complication after traumatic brain injury (TBI). Early identification of patients at increased thrombotic risk remains challenging. We aimed to develop and internally validate an interpretable machine-learning model for predicting LEDVT in patients with TBI.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      In this retrospective observational study, we analyzed 248 consecutive patients with TBI treated at Qinghai University Affiliated Hospital between August 2024 and December 2025. Patients were randomly assigned to a training cohort (\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f174) and an internal validation cohort (\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f74). A total of 39 demographic, clinical, and laboratory variables were screened. Feature selection was performed using least absolute shrinkage and selection operator (LASSO) regression, followed by multivariable logistic regression. Eight machine-learning algorithms were developed and compared. Model discrimination, calibration, and decision-curve performance were assessed, and the selected model was interpreted using Shapley additive explanations (SHAP).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>LEDVT occurred in 88 of 248 patients (35.5%). LASSO retained six variables for model development: age, platelet count, D-dimer, interleukin, lower limb fracture, and prophylactic anticoagulation. In multivariable logistic regression, D-dimer, interleukin, lower limb fracture, and prophylactic anticoagulation were significantly associated with LEDVT, whereas age and platelet count showed borderline associations. In the validation cohort, the Random Forest model showed strong discrimination, with an area under the receiver operating characteristic curve of 0.931 (95% CI 0.878\u20130.985), sensitivity of 78.8%, specificity of 95.1%, accuracy of 87.8%, precision of 92.9%, and F1 score of 0.852. SHAP analysis identified D-dimer, interleukin, prophylactic anticoagulation, age, platelet count, and lower limb fracture as the main contributors to model output.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>An interpretable Random Forest model based on routinely available clinical and laboratory variables showed good internal predictive performance for LEDVT after TBI. After external validation, this approach may help support early risk stratification and individualized surveillance in patients at increased thrombotic risk.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fneur.2026.1860019","type":"journal-article","created":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T04:26:15Z","timestamp":1785212775000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Explainable machine learning for predicting lower extremity deep vein thrombosis in traumatic brain injury patients: development of a SHAP-guided Random Forest model"],"prefix":"10.3389","volume":"17","author":[{"given":"Xujie","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Emergency ICU, The Affiliated Hospital of Qinghai University","place":["Xining, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuhui","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Neurology, The Second Hospital of Lanzhou University","place":["Lanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiqi","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Neurology, Xinhua Hospital Affiliated with Dalian University","place":["Dalian, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Medical Engineering and Translational Applications, Qinghai University Affiliated Hospital","place":["Xining, Qinghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zihou","family":"Xing","sequence":"additional","affiliation":[{"name":"Department of Medical Engineering and Translational Applications, Qinghai University Affiliated Hospital","place":["Xining, Qinghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Hou","sequence":"additional","affiliation":[{"name":"Department of Emergency ICU, The Affiliated Hospital of Qinghai University","place":["Xining, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhan","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Medical Engineering and Translational Applications, Qinghai University Affiliated Hospital","place":["Xining, Qinghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,28]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.15585\/mmwr.ss6609a1","article-title":"Traumatic brain injury-related emergency department visits, hospitalizations, and deaths - United States, 2007 and 2013","volume":"66","author":"Taylor","year":"2017","journal-title":"MMWR Surveill Summ"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"1255117","DOI":"10.3389\/fneur.2023.1255117","article-title":"The epidemiology of traumatic brain injuries in the fastest-paced city in China: a retrospective study","volume":"14","author":"Zou","year":"2023","journal-title":"Front Neurol"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"1252","DOI":"10.1080\/02699052.2025.2549941","article-title":"Pulmonary embolism in patients with traumatic brain injury in the United States during 2016-2020","volume":"39","author":"Garcia","year":"2025","journal-title":"Brain Inj"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1016\/j.surneu.2005.04.039","article-title":"A review of the risks and benefits of differing prophylaxis regimens for the treatment of deep venous thrombosis and pulmonary embolism in neurosurgery","volume":"64","author":"Epstein","year":"2005","journal-title":"Surg Neurol"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.jocn.2017.08.008","article-title":"Risk of deep vein thrombosis in neurosurgery: state of the art on prophylaxis protocols and best clinical practices","volume":"45","author":"Ganau","year":"2017","journal-title":"J Clin Neurosci"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"e510","DOI":"10.1016\/j.wneu.2017.10.012","article-title":"Evolution of prophylaxis protocols for venous thromboembolism in neurosurgery: results from a prospective comparative study on low-molecular-weight heparin, elastic stockings, and intermittent pneumatic compression devices","volume":"109","author":"Chibbaro","year":"2018","journal-title":"World Neurosurg"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1016\/s1474-4422(24)00454-x","article-title":"Unique considerations in the assessment and management of traumatic brain injury in older adults","volume":"24","author":"Depreitere","year":"2025","journal-title":"Lancet Neurol"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1080\/16501960410023732","article-title":"Incidence, risk factors and prevention of mild traumatic brain injury: results of the WHO collaborating Centre task force on mild traumatic brain injury","volume":"36","author":"Cassidy","year":"2004","journal-title":"J Rehabil Med"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"3187","DOI":"10.2147\/rmhp.S487375","article-title":"Risk estimation of deep venous thrombosis in polytrauma patients with traumatic brain injury a nomogram approach","volume":"17","author":"Zhang","year":"2024","journal-title":"Risk Manag Healthc Policy"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"1946","DOI":"10.1097\/ccm.0000000000002673","article-title":"Machine learning and sepsis: on the road to revolution","volume":"45","author":"Liu","year":"2017","journal-title":"Crit Care Med"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"1256958","DOI":"10.3389\/fneur.2023.1256958","article-title":"Ischemic and haemorrhagic stroke risk estimation using a machine-learning-based retinal image analysis (vol 13, 916966, 2022)","volume":"14","author":"Qu","year":"2023","journal-title":"Front Neurol"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1186\/s12911-025-02984-y","article-title":"Developing a high-performance AI model for spontaneous intracerebral hemorrhage mortality prediction using machine learning in ICU settings (vol. 25, 149, 2025)","author":"Yap","year":"2026","journal-title":"BMC Med Inform Decis Mak"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21203\/rs.3.rs-8613721\/v1","article-title":"A multifractal-guided machine learning framework for late post-traumatic seizure prediction following hemorrhagic traumatic brain injury","author":"Riabukhina","year":"2026","journal-title":"Research Square"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1007\/s12021-017-9335-z","article-title":"Mobile monitoring of traumatic brain injury in older adults: challenges and opportunities","volume":"15","author":"Irimia","year":"2017","journal-title":"Neuroinformatics"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1073","DOI":"10.1111\/j.1468-1331.2007.01908.x","article-title":"Correlation of a high D-dimer level with poor outcome in traumatic intracranial hemorrhage","volume":"14","author":"Kuo","year":"2007","journal-title":"Eur J Neurol"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"1276726","DOI":"10.3389\/fnmol.2023.1276726","article-title":"Plasma D-dimer levels are a biomarker for in-hospital complications and long-term mortality in patients with traumatic brain injury","volume":"16","author":"Chen","year":"2023","journal-title":"Front Mol Neurosci"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"1091","DOI":"10.1016\/j.apmr.2003.10.023","article-title":"Value of the D-dimer test in diagnosing deep vein thrombosis in rehabilitation inpatients","volume":"85","author":"Akman","year":"2004","journal-title":"Arch Phys Med Rehabil"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1161\/atvbaha.119.313137","article-title":"IL (interleukin)-6 contributes to deep vein thrombosis and is negatively regulated by miR-338-5p","volume":"40","author":"Zhang","year":"2020","journal-title":"Arterioscler Thromb Vasc Biol"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1046\/j.1365-2141.2002.03245.x","article-title":"Interleukin 8 and venous thrombosis: evidence for a role of inflammation in thrombosis","volume":"116","author":"van Aken","year":"2002","journal-title":"Br J Haematol"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"13176","DOI":"10.3390\/ijms232113176","article-title":"Immunothrombosis and the role of platelets in venous thromboembolic diseases","volume":"23","author":"Heestermans","year":"2022","journal-title":"Int J Mol Sci"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"e42997","DOI":"10.1097\/md.0000000000042997","article-title":"Risk factors for lower extremity deep vein thrombosis after intertrochanteric fracture of the femur and its response","volume":"104","author":"Wen","year":"2025","journal-title":"Medicine"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"e38439","DOI":"10.1097\/md.0000000000038439","article-title":"Risk factors for deep vein thrombosis after traumatic lower extremity fracture: a systematic review and meta-analysis","volume":"103","author":"Qian","year":"2024","journal-title":"Medicine (Baltimore)"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1016\/j.jclinepi.2020.03.005","article-title":"Machine learning algorithms performed no better than regression models for prognostication in traumatic brain injury","volume":"122","author":"Gravesteijn","year":"2020","journal-title":"J Clin Epidemiol"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"100295","DOI":"10.1016\/j.arrct.2023.100295","article-title":"Traumatic brain injury rehabilitation outcome prediction using machine learning methods","volume":"5","author":"Appiah Balaji","year":"2023","journal-title":"Arch Rehabil Res Clin Transl"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"960","DOI":"10.1038\/s41598-023-28188-w","article-title":"Prognosis prediction in traumatic brain injury patients using machine learning algorithms","volume":"13","author":"Khalili","year":"2023","journal-title":"Sci Rep"}],"container-title":["Frontiers in Neurology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1860019\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T04:26:16Z","timestamp":1785212776000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fneur.2026.1860019\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,28]]},"references-count":25,"alternative-id":["10.3389\/fneur.2026.1860019"],"URL":"https:\/\/doi.org\/10.3389\/fneur.2026.1860019","relation":{},"ISSN":["1664-2295"],"issn-type":[{"value":"1664-2295","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,28]]},"article-number":"1860019"}}