Researchers at King’s College London have found that AI-powered aging clocks can predict health and lifespan using blood metabolite data as reported by international media on Thursday.
According to a report by SciTechDaily, these clocks, based on machine learning algorithms, reveal that accelerated aging is linked to higher health risks, while decelerated aging shows only weak associations with better health.
AI aging clocks estimate biological age using blood metabolites, small molecules created during metabolism. The difference between biological age (MileAge) and actual age (MileAge delta) shows whether a person is aging faster or slower biologically.
Data from over 225,000 UK Biobank participants aged 40–69 was analyzed using 17 machine learning algorithms. Non-linear models, like Cubist regression, were most effective in capturing the link between metabolites, aging, and health.
People with accelerated aging (MileAge older than chronological age) were frailer, had higher risks of chronic illnesses and mortality, and shorter telomeres—a marker of cellular aging. Decelerated aging had weak links to good health.
AI aging clocks could help identify early health risks, allowing preventative measures before diseases develop. They may also empower individuals to track their health and make better lifestyle choices to age more healthily.
Key researcher Dr. Julian Mutz states, “Unlike chronological age, biological age can be modified. These aging clocks could guide both personal health decisions and preventative healthcare strategies.”
Another key researcher Professor Cathryn Lewis adds, “This study highlights the potential of big data analytics to advance biological aging clocks, making them a valuable tool for health research and decision-making.”
The study, published in Science Advances, marks a significant step in understanding how AI can transform aging research and healthcare.
