{getToc} $title={Table of Contents}
Summary
The study developed a metabolomic aging clock, MileAge, using machine learning algorithms and 168 plasma metabolites from 225,212 middle-aged and older adults. MileAge delta, the difference between metabolite-predicted and chronological age, was associated with health and aging markers, including frailty, telomere length, and mortality.
Highlights
- Metabolomic aging clock, MileAge, was developed using machine learning algorithms and 168 plasma metabolites.
- MileAge delta was associated with health and aging markers, including frailty, telomere length, and mortality.
- Individuals with an older metabolite-predicted than chronological age had a higher mortality risk.
- MileAge delta was more predictive of all-cause mortality than MetaboAge 2.0 delta.
- The study used a comprehensive comparison of machine learning algorithms for developing aging clocks.
- The study found that certain metabolomics-based risk scores should primarily be used to identify high-risk individuals.
- The study suggests that biological aging clocks may contribute to health risk assessments, complementing clinical biomarkers.
Key Insights
- The study demonstrated the utility of both linear and more complex nonlinear models in developing aging clocks, highlighting the importance of model selection for age estimation.
- The associations between most aging clocks, health and aging markers, and mortality demonstrate that these clocks capture biologically relevant information, which may find applications in health tracking and nutrition or in clinical trials.
- The study found that individuals with an older metabolite-predicted than chronological age, indicating accelerated aging, were frailer, had shorter telomeres, were more likely to have a chronic illness, rated their health worse, and had a higher mortality risk.
- The study suggests that certain metabolomics-based risk scores should primarily be used to identify high-risk individuals, as decelerated aging does not equivalently translate to better health outcomes.
- The study found that MileAge delta was more predictive of all-cause mortality than MetaboAge 2.0 delta, but less predictive of mortality than MetaboHealth, a metabolomic profile of mortality risk.
- The study demonstrated that the mortality hazard of individuals with a MileAge delta greater than one SD above the mean was higher in all strata, except for individuals with excellent health.
- The study suggests that biological aging clocks may contribute to health risk assessments, complementing clinical biomarkers, and provide an intuitive, year-based metric for health tracking that may help individuals proactively engage with their health.
Mindmap
Citation
Mutz, J., Iniesta, R., & Lewis, C. M. (2024). Metabolomic age (MileAge) predicts health and life span: A comparison of multiple machine learning algorithms. In Science Advances (Vol. 10, Issue 51). American Association for the Advancement of Science (AAAS). https://doi.org/10.1126/sciadv.adp3743