Aging is a complex process characterized by various phenotypic changes, including epigenetic modifications, inflammation, and metabolic dysregulation. Recent research has focused on DNA methylation clocks, which utilize DNA methylation profiles to estimate biological age and predict age-related outcomes. However, many existing clocks rely on linear models, which may not adequately capture the complexities of survival-related DNA methylation signatures.
In this study, researchers developed a heterogeneous stacked ensemble survival model using DNA methylation data from the Framingham Heart Study. They identified 190 CpG loci through elastic net Cox regression and constructed a survival prediction model by integrating five complementary survival models with a neural network meta-learner.
The performance of this survival model was evaluated in an external validation cohort, revealing strong predictive capabilities for all-cause mortality. Notably, the model outperformed PhenoAge and showed statistical comparability to GrimAge. However, it is important to note that these performance estimates were derived from cohorts of European ancestry and validated in postmenopausal women aged 50-79 years, suggesting that the findings may be most applicable to similar demographic groups.
What this study does not show
This study does not establish the clinical utility of the ensemble DNA methylation clock for predicting health outcomes beyond mortality, nor does it provide evidence of its applicability across diverse populations.
Evidence scorecard
- Analytic validity: Established
- Clinical validity: Partial
- Clinical utility: Not established
The evidence is based on primary research with human status unclassified.