StackAge: the biological aging clock that predicts chronic disease risk with clinical precision

StackAge, an ensemble machine-learning system integrating proteomic and metabolomic profiles from 30,376 UK Biobank participants, achieves 0.93 correlation with chronological age and substantially improves prediction of 12 chronic diseases, exceeding 90% accuracy for type 2 diabetes, Alzheimer's disease, and chronic kidney disease. Unlike conventional biological clocks—whose practical utility remains contested because we cannot verify whether they truly measure changes caused by rejuvenation therapies—StackAge explicitly links its aging rate estimates to disease risk, revealing that chronic inflammation, metabolic stress, and extracellular matrix remodeling are the underlying mechanisms. Mediation analysis demonstrates that modifiable lifestyle factors accelerate this biological trajectory and thereby increase susceptibility to cardiovascular, neurological, immune, and musculoskeletal disorders. For longevity-curious readers, this translates to a tangible, clinically actionable metric: not merely a biological age score, but a metabolic snapshot that justifies personalized preventive interventions before disease becomes symptomatic.