Wednesday, October 29, 2025

Science News: How old are you really? New AI tool reveals your body’s true age - Study

How old are you really? New AI tool reveals your body’s true age - Study

Although chronological age is the most commonly used measure, it doesn’t capture the individual complexities of aging.

By Esther Davis, Jerusalem Post, October 27, 2025

https://www.jpost.com/science/article-871702

The aging process (photo credit: SHUTTERSTOCK)

Researchers at Edith Cowan University (ECU) have recently developed a new way to measure biological age and find out how old you really are, and it might not be what you’d expect.

Whilst we generally measure age as chronological, i.e., how many years since you were born, the researchers have created an AI tool called AlphaSnake, which tracks your body’s age and can be used to help spot people at risk of age-related diseases earlier.

The study has been peer-reviewed and achieves 85% accuracy in predicting a person’s age. It found that the difference between a person's predicted and actual age (known as delta age) was associated with age-related health markers, such as cholesterol and blood sugar levels.

Co–author of the paper, Dr. Xingang Li, explained that although chronological age is the most commonly used measure, it doesn’t capture the complexities of aging at the individual level.

The study acknowledges that not everyone is aging at the same rate, as “In reality, some individuals remain healthy until into their 80s and 90s, whereas others may experience age-related decline much earlier.”

How did they do it?

By taking plasma samples from a group of 302 middle-aged individuals, the researchers were able to analyse markers in the body, including genetic, nutritional, disease-related, and general health factors, to create a comprehensive image of the subject’s biological age.

They then built two predictive models from the data and used them to estimate biological age. The biological and chronological ages were compared, and they found that the difference, delta age, could be used to predict risk for age-related health conditions.

The models hypothesized that combining the predictive features from each model would yield the optimal predictive feature set.

As a result, the researchers combined the two predictive models into one, known as AlphaSnake.

What did they find?

The age predicted from the analysed feature set can serve as an accurate measure alongside chronological age.

The delta age for the data is associated with blood pressure, cholesterol, and glucose levels. A positive delta age can be interpreted as reflecting more rapid biological aging, whilst a negative delta age shows slower biological aging.

This information can be used to predict who is at heightened risk of age-related disease, allowing doctors to more accurately inform patients’ medical care.

Co-author Dr. Islam said, “By measuring biological age and not just looking at someone’s birthdate, it could be very useful to better understand their health. If we know in advance, then we can change our lifestyle to better act on preserving our health and help prevent some of the damage our body may have experienced.”

The ECU team hopes that AI-driven biological age testing could soon become a regular part of medical check-ups - helping doctors predict diseases before they develop.