Development and validation of DNA methylation scores in two European cohorts augment 10-year risk prediction of type 2 diabetes

Early type 2 diabetes (T2D) risk assessment could help slow or prevent disease onset. Here the authors used blood-based DNA methylation data to develop 10-year risk prediction models for incident T2D. The results show an improvement in performance beyond standard risk factors typically used to predict the risk of T2D onset. Type 2 diabetes mellitus (T2D) presents a major health and economic burden that could be alleviated with improved early prediction and intervention. While standard risk factors have shown good predictive performance, we show that the use of blood-based DNA methylation information leads to a significant improvement in the prediction of 10-year T2D incidence risk. Previous studies have been largely constrained by linear assumptions, the use of cytosine-guanine pairs one-at-a-time and binary outcomes. We present a flexible approach (via an R package, MethylPipeR) based on a range of linear and tree-ensemble models that incorporate time-to-event data for prediction. Using the Generation Scotland cohort (training set n(cases) = 374, n(controls) = 9,461; test set n(cases) = 252, n(controls) = 4,526) our best-performing model (area under the receiver operating characteristic curve (AUC) = 0.872, area under the precision-recall curve (PRAUC) = 0.302) showed notable improvement in 10-year onset prediction beyond standard risk factors (AUC = 0.839, precision-recall AUC = 0.227). Replication was observed in the German-based KORA study (n = 1,451, n(cases) = 142, P = 1.6 x 10(-5)).

Automated summary

This study developed 10-year risk prediction models for incident type 2 diabetes (T2D) using blood-based DNA methylation data, showing improved performance beyond standard risk factors typically used for T2D prediction.