Blood-Based DNA Methylation Models Improve Short-term Cardiovascular Risk Stratification in Individuals With Type 2 Diabetes
Authors' conclusion
The DNAm-based models we have generated may improve risk stratification for short-term cardiovascular events in individuals with T2DM, providing a promising approach to refine identification of those at increased risk of MACE.
Study context
- Population
- T2D participants of the TOSCA.IT study; DNA methylation (DNAm) profiled in peripheral blood mononuclear cells at baseline
- Participants
- 305 participants
- Comparison
- Participants with major adverse cardiovascular events (MACE) within 5 years vs without
- T2DMACEn = 81
- T2Dn = 224reference
- Outcome
- Discriminative performance of DNAm-based models for incident MACE
- Follow-up
- 5 years
Methodological detailsnested in the TOSCA.IT trial, epigenome-wide DNA methylation profiling, least absolute shrinkage and selection operator (LASSO) logistic regression with stability selection, random split into training and internal test sets, five covariate-adjustment frameworks
- Nested in the TOSCA.IT trial
- Epigenome-wide DNA methylation profiling
- LASSO logistic regression with stability selection
- Random split into training and internal test sets
- Five covariate-adjustment frameworks
Performance
As reported in the abstract
Discrimination of five DNAm-based models in internal test cohort
ROC AUC range
0.915 to 0.937
Area under the precision-recall curve range
0.866 to 0.940
Further findings
Differentially methylated CpG sites across five frameworks
- Differentially methylated CpG sites
- 23,839, 21,529, 21,500, 12,114, and 7,101
- CpG predictors retained per model
- 22-26
- CpGs identified across all models, independently associated with MACE risk
- 12
Original publication
Blood-Based DNA Methylation Models Improve Short-term Cardiovascular Risk Stratification in Individuals With Type 2 Diabetes. Diabetes Care. Published 16 July 2026. doi:10.
Composed by AI from the published abstract and checked against it. How Briefs are made →