Interpretable machine learning models to predict venous thromboembolism in sepsis patients with type 2 diabetes mellitus
- 1Department of Emergency Surgery, Shaanxi Provincial People’s Hospital , ,
- 2Department of Hematology, The Affiliated Hospital of Northwest University, Xi’an No. 3 Hospital , ,
Abstract
Background: 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.
Methods: A total of 648 sepsis patients with T2DM admitted to Shaanxi Provincial People’s 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’s Hospital between November 2024 and December 2025, and an independent external validation cohort of 260 patients was retrospectively collected from Xi’an No. 3 Hospital (a separate tertiary care center) between November 2023 and December 2025. Six machine learning algorithms—Logistic Regression, Support Vector Machine (SVM), Multilayer Perceptron (MLP), LightGBM, XGBoost, and Random Forest—were 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.
Results: 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: 0.84–0.89).
Conclusions: 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.
Related
- A machine learning-driven and explainable prediction model for in-hospital mortality in patients with diabetes mellitus and congestive heart failure: integrating XGBoost and SHAP approaches.
- The Risk of Fractures in Patients with Type 1 Diabetes Mellitus
- Incidence of diabetes remission and association with microvascular and macrovascular complications in patients with newly diagnosed type 2 diabetes mellitus: a retrospective cohort study using real-world data in Thailand.
- Association of the Triglyceride–Glucose Index with Systolic and Diastolic Blood Pressure Among Patients With Type 2 Diabetes Mellitus
- Short-term clinical efficacy and recorded adverse events of semaglutide combined with dapagliflozin in patients with type 2 diabetes mellitus and chronic kidney disease
BibTeX
@article{ma2026interpretable,
title = {{Interpretable machine learning models to predict venous thromboembolism in sepsis patients with type 2 diabetes mellitus}},
author = {Longyang Ma and Xiaoyuan Yu and Qi Xin},
journal = {Frontiers in endocrinology},
year = {2026},
month = sep,
doi = {10.3389/fendo.2026.1958305},
url = {https://europepmc.org/article/PMC/PMC13661359},
note = {CC BY},
}
RIS
TY - JOUR
TI - Interpretable machine learning models to predict venous thromboembolism in sepsis patients with type 2 diabetes mellitus
AU - Longyang Ma
AU - Xiaoyuan Yu
AU - Qi Xin
PY - 2026
DA - 2026/09/30
JO - Frontiers in endocrinology
DO - 10.3389/fendo.2026.1958305
UR - https://europepmc.org/article/PMC/PMC13661359
AB - Background: 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. Methods: A total of 648 sepsis patients with T2DM admitted to Shaanxi Provincial People’s 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’s Hospital between November 2024 and December 2025, and an independent external validation cohort of 260 patients was retrospectively collected from Xi’an No. 3 Hospital (a separate tertiary care center) between November 2023 and December 2025. Six machine learning algorithms—Logistic Regression, Support Vector Machine (SVM), Multilayer Perceptron (MLP), LightGBM, XGBoost, and Random Forest—were 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. Results: 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: 0.84–0.89). Conclusions: 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.
SN - 1664-2392
ER -