StackAge: an ensemble-based clock for precise quantification of biological age using multi-omics data
A blood-based aging clock predicts disease risk years ahead and identifies lifestyle changes that may slow biological aging.
StackAge is an ensemble machine-learning aging clock integrating large-scale proteomics and metabolomics from 30,376 UK Biobank participants, achieving r=0.93 with chronological age and AUC exceeding 0.90 for T2DM, Alzheimer's, and CKD prediction. Biological aging rate, as estimated by the model, improved disease prediction beyond conventional omics features and identified modifiable lifestyle drivers of accelerated aging, positioning biological age as a clinically actionable precision-prevention biomarker.
What the study was
- Study design
- Cohort study (development + external validation using UK Biobank)
- Population
- UK Biobank participants (n=30,376) with matched plasma proteomic and metabolomic profiles
- Sample size
- 30376
- Category
- Diagnostics
- Maturity
- Validated
- Journal
- Brief Bioinform
Why it surfaced
Large-scale (n=30,376) validated multi-omics aging clock with AUC >0.90 for T2DM, Alzheimer's, and CKD prediction; provides a clinically actionable biological age metric for precision prevention stratification with identified modifiable lifestyle targets.
A plain-language summary of published research — not medical advice. Talk to a clinician about your own care.