Skip to content
Preprint · CC-BY via OpenAlex

AI-driven biological clocks of cardiac aging: Should we integrate ECG, metabolomic, and epigenetic signatures?

Salla Åkerblom, Manyi Jia, Shamin Tahasildar, Amna Khamis, Philippe Froguel, Amélie Bonnefond, Declan P. O’Regan, Nicolas Gambardella Le Novère, Marc‐Emmanuel Dumas

Research Square · 2026

Abstract

Abstract Background Cardiovascular diseases remain the leading cause of death globally, with age as the primary risk factor. Unlike chronological age, biological age aims to capture age-related physiological changes and may better predict health outcomes and disease risk. Recent advances in artificial intelligence have enabled the development of aging clocks, computational models that estimate biological age from diverse biomarker patterns. Main body This review examines three complementary approaches to quantifying cardiac and systemic aging. Epigenetic clocks, particularly second-generation models such as GrimAge, currently represent the most established molecular measures of biological aging and show strong associations with cardiovascular outcomes. AI-based electrocardiogram (ECG) clocks capture functional cardiac aging, with landmark studies demonstrating that ECG age gaps independently predict mortality and that accelerated ECG aging may confer up to 79% higher mortality risk. Metabolomic clocks provide complementary insight into systemic metabolic aging and reveal links between metabolic dysregulation and cardiovascular aging, including associations involving metabolites such as trimethylamine N-oxide (TMAO). However, current aging clocks face important limitations: single-modality approaches capture only one dimension of aging, the biological mechanisms underlying accelerated aging remain incompletely understood, and population generalizability remains limited. Conclusions Integration of ECG, metabolomic, and epigenetic data promises a paradigm shift from reactive disease management to proactive, personalized aging intervention. Understanding concordance and discordance between these complementary clocks may uncover distinct aging phenotypes and reveal modifiable biological pathways. Future research should focus on integrating multi-omics data within large longitudinal cohorts to build interpretable, population-generalizable models that can guide clinical interventions to extend healthspan(definition) and prevent cardiovascular disease.

◌ CITATION ONLY
Full text is not openly licensed for redistribution here. Read it at the source:

Read at source →

Provenance

Source
OpenAlex
DOI
10.21203/rs.3.rs-10155822/v1
Canonical
link ↗
Fetched
2026-11-04 MST

Cite this

APA
Åkerblom, S., Jia, M., Tahasildar, S., Khamis, A., Froguel, P., Bonnefond, A., O’Regan, D.P., Novère, N.G.L., &amp; Dumas, M. (2026). AI-driven biological clocks of cardiac aging: Should we integrate ECG, metabolomic, and epigenetic signatures?. <em>Research Square</em>. https://doi.org/10.21203/rs.3.rs-10155822/v1
Vancouver
Åkerblom S, Jia M, Tahasildar S, Khamis A, Froguel P, Bonnefond A, et al. AI-driven biological clocks of cardiac aging: Should we integrate ECG, metabolomic, and epigenetic signatures?. Research Square. 2026. doi:10.21203/rs.3.rs-10155822/v1.
BibTeX
@unpublished{salla2026AIdriv, title = {AI-driven biological clocks of cardiac aging: Should we integrate ECG, metabolomic, and epigenetic signatures?}, author = {Salla Åkerblom and Manyi Jia and Shamin Tahasildar and Amna Khamis and Philippe Froguel and Amélie Bonnefond and Declan P. O’Regan and Nicolas Gambardella Le Novère and Marc‐Emmanuel Dumas}, journal = {Research Square}, year = {2026}, doi = {10.21203/rs.3.rs-10155822/v1}, }

Research neighborhood

References, citing works, and semantically nearest findings. Click a node to open it.

Related findings