PREDICTING 30-DAY VENOUS THROMBOEMBOLISM FOLLOWING TOTAL JOINT REPLACEMENT, ACCOUNTING FOR TRENDS IN ANNUAL LENGTH OF STAY

Venous thromboembolism (VTE) is a common complication following total hip (THA) and total knee arthroplasty (TKA). Preoperative prediction remains difficult, particularly for models that account for the temporal trend in VTE rates. We aimed to evaluate whether annual mean length of stay (LOS) is associated with the incidence of VTE and develop a generalizable machine learning (ML) model to preoperatively predict the incidence of symptomatic VTE following THA and TKA. Annual incidence of 30-day postoperative VTE, deep vein thrombosis (DVT) and pulmonary embolism (PE) was calculated over six years (2014 to 2019) and tested for trend. Correlation between annual VTE rates and mean LOS was calculated. Univariate analysis of features was performed for association with incidence of VTE followed by utilization of predictive models (logistic regression, random forest, and XGBoost). Data was split into training and testing sets by year of surgery and different oversampling algorithms were used to address data imbalance (Figure 1). A total of 498,314 patients were included, with 0.88% developing a postoperative VTE within 30 days. VTE rates decreased from over 1.11% in 2014 to 0.76% in 2019 (p This study revealed a declining trend in VTE rates, strongly correlated to decreasing postoperative LOS and identified patient and surgery-specific factors associated with an increased risk of VTE. The development of more accurate ML models for VTE prediction may improve risk stratification, prevention, and monitoring for arthroplasty patients. For any figures or tables, please contact the authors directly.