Associated factors and predictive modeling of deep vein thrombosis in stroke patients undergoing rehabilitation
- 1Department of Rehabilitation, Huadong Hospital, Fudan University , ,
- 2Department of Ultrasonography, Huadong Hospital Affiliated to Fudan University , ,
Abstract
Background: This study aimed to identify factors associated with deep vein thrombosis (DVT) and to develop predictive models to facilitate individualized risk assessment in this population.
Methods: We retrospectively analyzed 240 patients with stroke admitted to a rehabilitation department, including 63 patients with DVT and 177 without DVT. Baseline demographic, clinical, and laboratory variables were collected. Univariate analysis was performed to screen variables potentially associated with DVT, followed by multivariable logistic regression to identify variables independently associated with DVT. In parallel, six machine-learning models were developed using all baseline variables. The full cohort was evaluated across 100 stratified 8:2 train-test splits, with repeated five-fold cross-validation performed within each training subset and corresponding held-out subsets used for testing. Model performance was assessed using the area under the receiver operating characteristic curve (AUC), and SHapley Additive exPlanations (SHAP) were used to enhance interpretability.
Results: Multivariable analysis identified lower Barthel Index [odds ratio (OR) = 0.979, p = 0.008], diabetes (OR = 0.434, p = 0.032), and malignant tumor (OR = 2.883, p = 0.014) as variables independently associated with DVT. The final logistic regression model achieved an AUC of 0.765. Among machine learning models, the random forest model demonstrated the highest mean cross-validated AUC (0.781 ± 0.022) and the highest mean held-out AUC across 100 stratified train-test splits (0.797 ± 0.062). SHAP analysis indicated that age, D-dimer level, Barthel Index, activated partial thromboplastin time (APTT), and disease course were the five most influential contributors to Random Forest predictions.
Conclusion: In conclusion, our findings support the use of integrated predictive approaches for DVT risk assessment and targeted screening in stroke rehabilitation settings.
Related
- Prevalence and factors associated with sarcopenia in individuals with stroke undergoing rehabilitation: A cross-sectional study
- H2FPEF Score and Charlson Comorbidity Index as Independent Predictors of Cardiovascular Outcomes in Elderly Patients Undergoing Geriatric Rehabilitation
- PO077 | BALANCING BLEEDING AND THROMBOSIS: SAFETY OF LOW-MOLECULAR-WEIGHT HEPARIN THROMBOPROPHYLAXIS IN PATIENTS WITH HEMOPHILIA UNDERGOING MAJOR SURGERY
- Pulmonary Rehabilitation for Patients Undergoing Hematopoietic Stem Cell Transplantation: A Systematic Review and Meta-Analysis
- Patterns of Falls and Fractures Among Older Adults Undergoing Rehabilitation After Fall-Related Fractures: A Retrospective Study in Croatia.
BibTeX
@article{wang2026associated,
title = {{Associated factors and predictive modeling of deep vein thrombosis in stroke patients undergoing rehabilitation}},
author = {Yaping Wang and Weilan Jiang and Yumeng Xing and Yongjun Zheng and Jiejiao Zheng},
journal = {Frontiers in neurology},
year = {2026},
month = sep,
doi = {10.3389/fneur.2026.1896717},
url = {https://europepmc.org/article/PMC/PMC13661388},
note = {CC BY},
}
RIS
TY - JOUR
TI - Associated factors and predictive modeling of deep vein thrombosis in stroke patients undergoing rehabilitation
AU - Yaping Wang
AU - Weilan Jiang
AU - Yumeng Xing
AU - Yongjun Zheng
AU - Jiejiao Zheng
PY - 2026
DA - 2026/09/30
JO - Frontiers in neurology
DO - 10.3389/fneur.2026.1896717
UR - https://europepmc.org/article/PMC/PMC13661388
AB - Background: This study aimed to identify factors associated with deep vein thrombosis (DVT) and to develop predictive models to facilitate individualized risk assessment in this population. Methods: We retrospectively analyzed 240 patients with stroke admitted to a rehabilitation department, including 63 patients with DVT and 177 without DVT. Baseline demographic, clinical, and laboratory variables were collected. Univariate analysis was performed to screen variables potentially associated with DVT, followed by multivariable logistic regression to identify variables independently associated with DVT. In parallel, six machine-learning models were developed using all baseline variables. The full cohort was evaluated across 100 stratified 8:2 train-test splits, with repeated five-fold cross-validation performed within each training subset and corresponding held-out subsets used for testing. Model performance was assessed using the area under the receiver operating characteristic curve (AUC), and SHapley Additive exPlanations (SHAP) were used to enhance interpretability. Results: Multivariable analysis identified lower Barthel Index [odds ratio (OR) = 0.979, p = 0.008], diabetes (OR = 0.434, p = 0.032), and malignant tumor (OR = 2.883, p = 0.014) as variables independently associated with DVT. The final logistic regression model achieved an AUC of 0.765. Among machine learning models, the random forest model demonstrated the highest mean cross-validated AUC (0.781 ± 0.022) and the highest mean held-out AUC across 100 stratified train-test splits (0.797 ± 0.062). SHAP analysis indicated that age, D-dimer level, Barthel Index, activated partial thromboplastin time (APTT), and disease course were the five most influential contributors to Random Forest predictions. Conclusion: In conclusion, our findings support the use of integrated predictive approaches for DVT risk assessment and targeted screening in stroke rehabilitation settings.
SN - 1664-2295
ER -