Machine Learning Prediction of Cardiovascular Events in Men with Prostate Cancer Receiving Androgen Deprivation Therapy

Background Identifying prostate cancer (PCa) patients at high cardiovascular (CV) risk prior to androgen deprivation therapy (ADT) remains challenging, and no validated tool exists for major adverse cardiovascular event (MACE) risk stratification. To develop and validate a machine learning–based model predicting 10-year MACE risk in PCa patients receiving ADT. Methods In this retrospective prognostic study, we analyzed PCa patients treated with ADT from the Taiwan Cancer Registry (2010–2021), with follow-up through 2022. Fifteen sociodemographic, comorbidity, and ADT-related variables were evaluated. The cohort was split into derivation (n = 27,257) and validation (n = 11,681) sets. A random survival forest (RSF) model incorporating eight selected variables was developed to predict MACEs (ischemic stroke, myocardial infarction, and CV death), with non-CV death treated as a competing risk. Results Over a mean follow-up of 4.26 years, 5,681 patients (14.6%) experienced MACEs. The final model identified eight predictors: age ≥ 75 years, coronary heart disease, atrial fibrillation, heart failure, prior myocardial infarction, peripheral arterial disease, hypertension, and ADT type (GnRH agonist or orchiectomy). Both the initial 15-variable and final 8-variable RSF models demonstrated satisfactory discrimination, with area under the curve (AUC) of 81.2% (95% CI: 80.5–81.9%) and 78.7% (95% CI: 78.0–79.4%), respectively. A positive correlation was observed between the number of risk factors and the incidence of MACEs. Conclusions We developed and validated an 8-variable machine learning model that effectively stratifies MACE risk in PCa patients undergoing ADT, supporting targeted CV risk assessment before treatment initiation.