DNA methylation age is associated with mortality in a longitudinal Danish twin study

Abstract

An epigenetic profile defining the DNA methylation age (DNAm age) of an individual has been suggested to be a biomarker of aging, and thus possibly providing a tool for assessment of health and mortality. In this study, we estimated the DNAm age of 378 Danish twins, age 30-82 years, and furthermore included a 10-year longitudinal study of the 86 oldest-old twins (mean age of 86.1 at follow-up), which subsequently were followed for mortality for 8 years. We found that the DNAm age is highly correlated with chronological age across all age groups (r = 0.97), but that the rate of change of DNAm age decreases with age. The results may in part be explained by selective mortality of those with a high DNAm age. This hypothesis was supported by a classical survival analysis showing a 35% (4-77%) increased mortality risk for each 5-year increase in the DNAm age vs. chronological age. Furthermore, the intrapair twin analysis revealed a more-than-double mortality risk for the DNAm oldest twin compared to the co-twin and a 'dose-response pattern' with the odds of dying first increasing 3.2 (1.05-10.1) times per 5-year DNAm age difference within twin pairs, thus showing a stronger association of DNAm age with mortality in the oldest-old when controlling for familial factors. In conclusion, our results support that DNAm age qualifies as a biomarker of aging.

Keywords: DNA methylation; biological age; biomarker; epigenetic clock; mortality; twins.

Figure 1

Horvath DNAm age against chronological age. (a) Correlation between the methylation age using the Horvath model. The relation is visualized by a smoothing spline. (b) DNAm age trajectories of each individual in the longitudinal study of oldest‐olds. The lines are colored by intervals of slow to fast agers, and the histogram indicates the distribution within the intervals.

Figure 2

Mortality of the oldest twins according to intrapair DNAm age difference at follow‐up and difference in change over 10 years. The plots display the proportion of twins where the DNAm oldest twins died first (Proportion dead), for all twins and divided into groups with increasing intrapair difference. The numbers of twin pairs in each group are given in brackets, and the P‐values are shown below the lines on the left panel and above the lines on the right.