Westerman K, Fernández‐Sanlés A, Patil P, et al. - Researchers studied existing DNA methylation data obtained utilizing the Illumina HumanMethylation450 microarray to develop a predictor of cardiovascular disease (CVD) risk across 3 cohorts: Women's Health Initiative, Framingham Heart Study Offspring Cohort, and Lothian Birth Cohorts. They trained Cox proportional hazards‐based elastic net regressions for incident CVD individually in each cohort as well as applied a recently proposed cross‐study learning approach to combine these separate scores into an ensemble predictor. Experts identified the link of the methylation‐based risk score with CVD time‐to‐event in a held‐out fraction of the Framingham data set, as well as noted that this score enabled myocardial infarction status prediction in the independent REGICOR (Girona Heart Registry) data set. These links persisted following adjustment for traditional cardiovascular risk factors as well as were identified to be similar to those from elastic net models trained on a directly merged data set. Overall, this work affords proof‐of‐concept for a genome‐wide, CVD‐specific epigenomic risk score. Findings are also suggestive of the likely usefulness of the DNA methylation data in allowing the identification of high‐risk people who would be missed by alternative risk metrics.