Development and Validation of a Prediction Model for Venous Thromboembolic Events Following Hematoma Evacuation in Patients with Spontaneous Intracerebral Hemorrhage

Abstract Objectives To develop and validate a novel prediction model for venous thromboembolism (VTE) after hematoma evacuation in spontaneous intracerebral hemorrhage (sICH) patients. Methods sICH patients who underwent hematoma evacuation from January 2022 to December 2024 were retrospectively analyzed in two tertiary hospitals. The cohort was divided into a development cohort and a validation cohort. Clinical data and laboratory test results were collected. Multivariate logistic regression was used to identify independent predictors of VTE at 30 days after surgery and Nomogram was constructed. The model performance was tested with the validation cohort and assessed using the C-index, calibration curve, Hosmer-Lemeshow test, decision curve analysis (DCA), and clinical impact curve (CIC). Results A total of 456 patients were enrolled in the study, 346 of whom were used in the training cohort and 110 in the validation cohort. The C-index and Brier score of the nomogram in the training set were 0.902 and 0.072, respectively, and the correction values after internal verification were 0.805 and 0.026, respectively. The calibration curve showed favorable consistency between the prediction of the nomogram and actual observations in both the training and validation cohorts. In addition, DCA and CIC confirmed the clinical utility of the nomogram constructed to predict postoperative VTE in sICH patients. Conclusion This first surgery-specific nomogram integrates five perioperative variables to accurately predict VTE risk post-evacuation in sICH patients. It enables early targeted prophylaxis, potentially reducing preventable morbidity.