Predicting Lower Extremity Deep Venous Thrombosis in Patients with aneurysmal subarachnoid hemorrhage:A Machine Learning Study

Fengfeng Jiang¹Chenxing Ye¹Danfeng Yu¹Feng Chen¹Wei Xu¹Pingyou He¹Chengwei Zhang²Tong Minfeng^1*Xiang Bao^1*

• ¹Department of Neurosurgery, Affiliated Jinhua Hospital, Zhejiang University School of Medicine, Jinhua, China
• ²Department of traumatology, Affiliated Hangzhou First People's Hospital, Westlake University School of Medicine,, Hangzhou, China

Lower extremity deep venous thrombosis (LEDVT) is a common and serious complication following aneurysmal subarachnoid hemorrhage (aSAH). This study aimed to develop and validate machine learning (ML) models for early prediction of LEDVT in aSAH patients treated with endovascular therapy. A retrospective analysis was conducted using data from 593 patients for model training and internal validation, and 142 patients from an external center for validation. Six clinical variables were identified through LASSO and multivariate logistic regression. Among seven ML algorithms, the XGBoost model demonstrated the best predictive performance, with an AUC of 0.88 in internal validation and 0.80 in external validation. A web-based risk calculator was established to facilitate clinical implementation. The proposed model offers a promising tool to identify high-risk patients and support early preventive decision-making in the management of aSAH.