Key result
Survival forest model predicts MACE with ~86% AUC in prostate cancer patients taking abiraterone or enzalutamide.
Why the study?
Identifying cardiovascular risk factors in metastatic prostate cancer patients before starting androgen receptor pathway inhibitors is important yet challenging.
Can a machine learning random survival forest model accurately predict major adverse cardiovascular events in metastatic prostate cancer patients receiving abiraterone or enzalutamide?
Cohort (n=4,739)
Yes
Can a machine learning random survival forest model accurately predict major adverse cardiovascular events in metastatic prostate cancer patients receiving abiraterone or enzalutamide?
Effect estimate: AUC 85.5%
Absolute Event Rate: 10.9% vs 11.3%
A machine learning model utilizing five clinical variables demonstrated strong predictive accuracy for major adverse cardiovascular events in prostate cancer patients receiving androgen receptor pathway inhibitors.
May aid MACE risk stratification on abiraterone or enzalutamide; leaves open prospective validation before clinical adoption.
Purpose: The identification of cardiovascular risk factors in metastatic prostate cancer (PCa) patients prior to the initiation of androgen receptor pathway inhibitors (ARPIs) is important yet challenging. Methods and Results: A nationwide cohort study was conducted utilizing data from the National Health Insurance Research Database containing the Taiwan Cancer Registry. The study population comprised 4739 PCa patients who received abiraterone or enzalutamide between 1 January 2014, and 28 February 2022. The cohort was divided into a training set (n = 3318) and a validation set (n = 1421). Machine learning techniques with random survival forest (RSF) model incorporating 16 variables was developed to predict major adverse cardiovascular events (MACEs). Over a mean follow-up period of 2.1 years, MACEs occurred in 10.9% and 11.3% of the training and validation cohorts, respectively. The RSF model identified five key predictive indicators: age < 65 or ≥75 years, heart failure, stroke, hypertension, and myocardial infarction. The model exhibited robust performance, achieving an area under the curve (AUC) of 85.1% in the training set and demonstrating strong external validity with an AUC of 85.5% in the validation cohort. A positive correlation was observed between the number of risk factors and the incidence of MACEs. Conclusions: This machine learning approach identified five predictors of MACEs in PCa patients receiving ARPIs. These findings highlight the need for comprehensive cardiovascular risk assessment and vigilant monitoring in this patient population.
No takes yet. Share an insight, caveat, or question.
Chen et al. (2025) conducted a cohort in metastatic prostate cancer (n=4,739). Random survival forest (RSF) model was evaluated on Major adverse cardiovascular events (MACEs) (AUC 85.5%). A random survival forest model identified five key predictors of MACEs in prostate cancer patients receiving abiraterone or enzalutamide, achieving an AUC of 85.5% in the validation cohort.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: