Prediction of risk factors for preoperative deep vein thrombosis in patients with pelvic fracture
Yu‐Fen Chen, Jingyuan He, Xia Pan
Abstract
Objective: This study aims to develop a preoperative risk assessment tool for deep vein thrombosis (DVT) in pelvic fracture patients, offering evidence-based guidance for surgeons. Methods: A cohort of 400 pelvic fracture patients was analyzed. Ten candidate predictors were initially identified via LASSO regression from 25 clinical variables. Four independent risk factors-emergency abdominal surgery, Injury Severity Score (ISS), serum creatinine levels, and aspartate aminotransferase (AST)-were subsequently incorporated into a multivariate logistic regression model. A nomogram was developed using R software, with calibration accuracy assessed via the rms package and clinical utility evaluated through decision curve analysis (DCA) using the ggDCA package. Results: The final model demonstrated excellent discriminative ability, with area under the curve (AUC) values of 0.88 (95% CI: 0.81-0.93) in the training cohort and 0.88 (95% CI: 0.80-0.95) in the validation cohort. Calibration curves confirmed strong alignment between predicted and observed DVT probabilities, while DCA highlighted the nomogram's clinical applicability across a wide risk threshold range. Conclusion: The validated nomogram provides a reliable preoperative tool for stratifying DVT risk in pelvic fracture patients. By enabling early identification of high-risk individuals, this model supports targeted prophylactic interventions, ultimately enhancing perioperative safety and patient outcomes.