{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T05:01:40Z","timestamp":1790744500766,"version":"4.1.0"},"reference-count":29,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T00:00:00Z","timestamp":1790726400000},"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. Endocrinol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Sepsis patients with type 2 diabetes mellitus (T2DM) face a substantially elevated risk of venous thromboembolism (VTE), yet prediction tools tailored for this population are lacking. This study aimed to develop and validate interpretable machine learning models for predicting in-hospital VTE in septic patients with T2DM.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A total of 648 sepsis patients with T2DM admitted to Shaanxi Provincial People\u2019s Hospital between January 2020 and October 2024 were included in this retrospective cohort study, an internal validation cohort of 303 patients was retrospectively collected from Shaanxi Provincial People\u2019s Hospital between November 2024 and December 2025, and an independent external validation cohort of 260 patients was retrospectively collected from Xi\u2019an No. 3 Hospital (a separate tertiary care center) between November 2023 and December 2025. Six machine learning algorithms\u2014Logistic Regression, Support Vector Machine (SVM), Multilayer Perceptron (MLP), LightGBM, XGBoost, and Random Forest\u2014were developed and compared. Feature selection was performed using the Boruta algorithm combined with forward sequential feature selection. Model performance was evaluated by discrimination (area under the receiver operating characteristic curve, AUC), calibration (calibratin plots and Brier scores), and clinical utility (decision curve analysis). Model interpretability was enhanced using SHAP analysis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Among the 648 internal patients, 115 (17.7%) developed VTE. The Boruta algorithm and forward sequential feature selection identified five key predictors: D-dimer, C-reactive protein (CRP), activated partial thromboplastin time (APTT), international normalized ratio (INR), and fibrin degradation products (FDP). Among the six algorithms, LightGBM achieved the best overall performance, with an AUC of 0.9025 in the test set, 0.8048 in the internal validation cohort, and 0.8902 in the external validation cohort. Calibration curves demonstrated good agreement between predicted and observed outcomes, and decision curve analysis confirmed positive net clinical benefit across a wide range of threshold probabilities. SHAP analysis revealed that elevated D-dimer, CRP, INR, and FDP, together with shortened APTT, were the strongest drivers of VTE risk. Sensitivity analyses excluding D-dimer-driven cases, removing the D-dimer feature, and restricting to symptomatic VTE yielded consistent results (AUC range: 0.84\u20130.89).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The LightGBM model incorporating five readily available coagulation and inflammatory markers accurately predicts in-hospital VTE in sepsis patients with T2DM, with robust discrimination, calibration, and clinical utility. SHAP-based interpretability enhances transparency and may facilitate personalized risk stratification and informed thromboprophylaxis decisions in this high-risk population.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fendo.2026.1958305","type":"journal-article","created":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T04:53:31Z","timestamp":1790744011000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Interpretable machine learning models to predict venous thromboembolism in sepsis patients with type 2 diabetes mellitus"],"prefix":"10.3389","volume":"17","author":[{"given":"Longyang","family":"Ma","sequence":"first","affiliation":[{"name":"Department of Emergency Surgery, Shaanxi Provincial People\u2019s Hospital","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyuan","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Hematology, The Affiliated Hospital of Northwest University, Xi\u2019an No. 3 Hospital","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Xin","sequence":"additional","affiliation":[{"name":"Department of Emergency Surgery, Shaanxi Provincial People\u2019s Hospital","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,30]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1016\/s0140-6736(20)32658-1","article-title":"Venous thromboembolism","volume":"398","author":"Khan","year":"2021","journal-title":"Lancet"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1182\/bloodadvances.2019000561","article-title":"Metabolic syndrome increases risk of venous thromboembolism recurrence after acute deep vein thrombosis","volume":"4","author":"Stewart","year":"2020","journal-title":"Blood Adv"},{"key":"B3","article-title":"Nomogram and machine learning models for predicting in-hospital mortality in sepsis patients with deep vein thrombosis","volume":"50","author":"Duan","year":"2025","journal-title":"Zhong Nan Da Xue Xue Bao Yi Xue Ban"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/j.diabres.2022.110190","article-title":"Diabetes mellitus is associated with a higher relative risk for venous thromboembolism in females than in males","volume":"194","author":"Deischinger","year":"2022","journal-title":"Diabetes Res Clin Pract"},{"key":"B5","doi-asserted-by":"publisher","first-page":"1738139","DOI":"10.3389\/fcvm.2025.1738139","article-title":"A comprehensive review of venous thromboembolism risk assessment models for hospitalized medical patients: comparative evidence, implementation challenges, and future directions","volume":"12","author":"Alfehaid","year":"2025","journal-title":"Front Cardiovasc Med"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1007\/s00592-021-01728-4","article-title":"Type 2 diabetes mellitus and sepsis: state of the art, certainties and missing evidence","volume":"58","author":"Costantini","year":"2021","journal-title":"Acta Diabetol"},{"key":"B7","doi-asserted-by":"publisher","first-page":"60","DOI":"10.21037\/atm-25-83","article-title":"Smart emergency care: a narrative review of predictive machine learning models","volume":"13","author":"Olawade","year":"2025","journal-title":"Ann Transl Med"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.3389\/fphys.2025.1664470","article-title":"Application of artificial intelligence in risk assessment and management of venous thromboembolism: scoping review","volume":"16","author":"Gu","year":"2025","journal-title":"Front Physiol"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1016\/j.thromres.2025.109507","article-title":"Systematic review of a machine learning model for prediction of venous thromboembolism risk","volume":"256","author":"Ge","year":"2025","journal-title":"Thromb Res"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1016\/j.csbj.2024.08.005","article-title":"Unveiling the black box: a systematic review of Explainable Artificial Intelligence in medical image analysis","volume":"24","author":"Muhammad","year":"2024","journal-title":"Comput Struct Biotechnol J"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2026.106287","article-title":"Clinician preferences for explainable AI in critical care: a comparative study of interpretable models and visualizations for intubation decision support","volume":"210","author":"Xian","year":"2026","journal-title":"Int J Med Inform"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2016.0287","article-title":"The third international consensus definitions for sepsis and septic shock (Sepsis-3)","volume":"315","author":"Singer","year":"2016","journal-title":"Jama"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.2337\/dc22-S002","article-title":"Classification and diagnosis of diabetes: standards of medical care in diabetes-2022","volume":"45","author":"Boris","year":"2022","journal-title":"Diabetes Care"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.m2177","article-title":"Pulmonary embolism: update on management and controversies","volume":"370","author":"Duffett","year":"2020","journal-title":"Bmj"},{"key":"B15","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1186\/s12959-025-00728-6","article-title":"The prevalence and risk factors of pulmonary embolism in patients with chronic obstructive pulmonary disease: a systematic review and meta-analysis","volume":"23","author":"Li","year":"2025","journal-title":"Thromb J"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1177\/10760296251388989","article-title":"Risk factors associated with venous thromboembolism in individuals with COPD: A systematic review and meta-analysis","volume":"31","author":"Huang","year":"2025","journal-title":"Clin Appl Thromb Hemost"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1080\/0886022x.2024.2431149","article-title":"Risk factors for venous thromboembolism in patients with chronic kidney disease: a systematic review and meta-analysis","volume":"46","author":"Zhan","year":"2024","journal-title":"Ren Fail"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejim.2025.106448","article-title":"Venous thromboembolism associated with infections: a systematic review and meta-analysis","volume":"142","author":"Stathopoulos","year":"2025","journal-title":"Eur J Intern Med"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1016\/j.cca.2025.120558","article-title":"Diagnostic utility of combined coagulation and inflammatory biomarkers in sepsis stratification: a retrospective study","volume":"578","author":"Ding","year":"2026","journal-title":"Clin Chim Acta"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2025.1681621","article-title":"Early prediction of sepsis-induced coagulopathy in the ICU using interpretable machine learning: a multi-center retrospective cohort study","volume":"12","author":"Sha","year":"2025","journal-title":"Front Med (Lausanne)"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1080\/07853890.2026.2614222","article-title":"Risk factors of venous thromboembolism in ICU patients: a systematic review and meta-analysis","volume":"58","author":"Yang","year":"2026","journal-title":"Ann Med"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.5847\/wjem.j.1920-8642.2025.036","article-title":"The role of early changes in routine coagulation tests in predicting the occurrence and prognosis of sepsis","volume":"16","author":"Chen","year":"2025","journal-title":"World J Emerg Med"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1055\/s-0028-1104539","article-title":"Activated partial thromboplastin time: new tricks for an old dogma","volume":"34","author":"Lippi","year":"2008","journal-title":"Semin Thromb Hemost"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1016\/j.thromres.2025.109536","article-title":"von Willebrand factor and fibrin monomer - induced septic shock coagulation typing: Clinical comparison between thrombotic thrombocytopenic purpura - like syndrome and sepsis - induced coagulopathy with prognostic implications","volume":"256","author":"Liu","year":"2025","journal-title":"Thromb Res"},{"key":"B25","doi-asserted-by":"publisher","first-page":"763","DOI":"10.3390\/nu18050763","article-title":"Insulin resistance and platelet hyperactivity: hematological insights and nutritional strategies for vascular protection","volume":"18","author":"Mohammadian","year":"2026","journal-title":"Nutrients"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.2196\/80969","article-title":"Machine learning algorithms to predict venous thromboembolism in patients with sepsis in the intensive care unit: multicenter retrospective study","volume":"14","author":"Zhang","year":"2026","journal-title":"JMIR Med Inform"},{"key":"B27","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1186\/s12959-023-00526-y","article-title":"Association between inflammatory biomarkers and venous thromboembolism: a systematic review and meta-analysis","volume":"21","author":"Ding","year":"2023","journal-title":"Thromb J"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.2147\/jir.s504184","article-title":"The mechanisms of sepsis induced coagulation dysfunction and its treatment","volume":"18","author":"Zhu","year":"2025","journal-title":"J Inflammation Res"},{"key":"B29","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1186\/s12911-025-03076-7","article-title":"Nonlinear association between visceral fat metabolism score and heart failure: insights from LightGBM modeling and SHAP-Driven feature interpretation in NHANES","volume":"25","author":"Cheng","year":"2025","journal-title":"BMC Med Inform Decis Mak"}],"container-title":["Frontiers in Endocrinology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2026.1958305\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T04:53:38Z","timestamp":1790744018000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fendo.2026.1958305\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,30]]},"references-count":29,"alternative-id":["10.3389\/fendo.2026.1958305"],"URL":"https:\/\/doi.org\/10.3389\/fendo.2026.1958305","relation":{},"ISSN":["1664-2392"],"issn-type":[{"value":"1664-2392","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,30]]},"article-number":"1958305"}}