A novel cardiovascular disease risk score for prediction of atherosclerotic disease events in men with prostate cancer

Background: Prostate cancer patients (PC) face an elevated risk of both developing atherosclerotic cardiovascular disease (ASCVD). The American College of Cardiology Pooled Cohort Equations (PCE) for ASCVD predictions may lack accuracy. Methods: Males $18 years, diagnosed with PC between 2005-2012 at a hybrid academic-community practice were included. Using XGBoost algorithm we developed using a training subset of the cohort (50% train + 25% test), ranked 33 covariates (including demographic, treatment-related and social determinants of health (SDOH) information) for ASCVD prediction using SHAP (Shapley additive explanations) values. The top 10 predictors were transformed in a predictive equation using logistic regression models. This equation was tested in the cohort validation subset (25%), and subsequently compared to the PCE risk score. Results: We included 1,506 patients, with a median age of 67 (IQR 60–74) years, 13.8% had advanced stage disease (TNM III-IV), 1.5% had high risk PC (Gleason 8–10), and 20.5% received androgen deprivation therapy (ADT). Of those, 10.4% had a 10-year ASCVD risk. The PCE had an area under the curve (AUC)=0.61 and underestimated ASCVD in 0.9% (mean risk=20.1% [95% CI 17.2–23.0] vs. mean predicted risk=19.2% [95% CI 18.6–19.8]). The equation pooled from the top-10 predictors of the ML algorithm (C-index=0.78 [95% CI 0.75–0.81]) achieved an AUC=0.71 (Table). Conclusions: Conventional PCE tend to underestimate ASCVD risk in males with PC. A cancer-specific model inclusive of SDOH exhibits good performance for predicting ASCVD risk in this population. Research Sponsor: None.