AI reveals the body’s true age by reading hidden markers in blood

Age is more than just the number of years since you arrived on Earth. Two people born on the same day can live entirely different biological lives. One may still hike up mountains at 80, while the other struggles to climb stairs at 60.

What separates them isn’t luck – it’s how their bodies have aged beneath the surface. Scientists from Edith Cowan University (ECU) believe they can now measure that hidden process more precisely than ever before.

AI decodes how we age

Researchers from ECU, Royal Prince Alfred Hospital in Sydney, and Shantou University Medical College in China worked together to build a new biological clock called gtAge. Instead of just counting years, it reads changes written inside our blood.

The team examined two powerful markers. One was the IgG N-glycome, a pattern of sugars attached to antibodies that shift as we grow older. The other was the transcriptome, a snapshot of how genes inside blood cells turn on and off.

When the researchers combined both types of data using an artificial intelligence method called deep reinforcement learning, the results surprised them.

Their new tool predicted a person’s age with 85 percent accuracy – more precise than previous approaches that relied on a single measure. It didn’t just guess the number of years. It read how the body truly feels and functions.

Blood reveals real age

Every drop of blood carries traces of our biological history. The IgG N-glycome reflects how the immune system evolves and weakens with time, while the transcriptome shows how genes respond to stress, diet, and disease. Blending these signals gave gtAge a wider lens to view aging.

The study also examined something called delta age, the difference between biological and actual age. People with higher delta ages had elevated cholesterol, triglycerides, blood sugar, and glycated hemoglobin.

Those with lower delta ages showed healthier levels of high-density lipoprotein, the so-called good cholesterol. In short, gtAge didn’t just measure time – it revealed how well or poorly a body had weathered it.

These findings matter because they connect biological age to real health outcomes. A person whose biological age runs ahead of their birth age could face greater risks of heart disease or diabetes.

Someone who clocks younger biologically might be benefiting from protective genes, habits, or environments. The gtAge model provides a map of those hidden differences.

Biological age matters more

Study co-author Dr. Xingang Li, a postdoctoral researcher in ECU’s School of Medical and Health Sciences, explained why counting birthdays misses so much.

“In reality, some individuals remain healthy until into their 80s and 90s, whereas others may experience age-related decline much earlier,” said Dr. Li.

“This discrepancy can be attributed to differences in biological age, which integrates genetic, lifestyle, nutritional, disease-related, and general health factors to accurately reflect the true biological aging process.”

Dr. Li added that gtAge explains 85.3 percent of the variation in chronological age.

“By merging IgG N-glycome data and transcriptome data, we have elevated the accuracy of biological aging estimation,” he said. “It links to real health risks and could help spot people at risk of age-related diseases earlier.”

Chronological age tells how long someone has lived. Biological age shows how well the body has held up. That difference could redefine how doctors approach prevention and treatment in the years ahead.

AI makes age measurable

Building gtAge required more than biology. It needed computing power that could think beyond human limits. ECU Senior Lecturer of Computer Science, Dr. Syed Islam, led that side of the project.

“To improve age prediction using integrated multiomics data, we developed a custom AI tool named AlphaSnake, powered by deep reinforcement learning,” Dr. Islam said.

“This algorithm works by picking the most useful data points from the two different biological sources, avoiding the pitfalls of just blindly blending data.”

The AI learned how to recognize complex relationships between molecular markers. Instead of combining everything at once, it selectively chose the features that mattered most.

This focused learning process allowed gtAge to outperform older systems that simply added data together.

To test the accuracy, the team analyzed samples from 302 middle-aged adults in Western Australia’s Busselton Healthy Aging Study. The clock’s predictions closely matched each participant’s biological profile, confirming its reliability.

Reading health in advance

The promise of gtAge reaches beyond research labs. For a country like Australia, where the population is aging, a tool like this could change how healthcare works.

“By measuring biological age and not just looking at someone’s birthdate, it could be very useful to better understand their health,” Dr. Islam said.

“If we know in advance, then we can change our lifestyle to better act on preserving our health and help prevent some of the damages our body may have experienced.”

Imagine visiting a clinic and learning that your body’s true age is five years older than your actual one. That insight could push you to eat differently, exercise more, or seek treatment early. Biological clocks like gtAge bring that possibility within reach.

Future of aging science

The research highlights how blending biology with artificial intelligence can reveal the invisible rhythm of human aging.

Future versions of gtAge may include more biological layers, such as proteins or metabolites, making the clock even sharper. As technology improves, doctors may soon track aging like they track blood pressure or cholesterol.

The message is clear: aging isn’t uniform. It’s personal, shaped by genes, habits, and the environment. gtAge doesn’t just count time – it reads the language written in our cells. And by learning to read it, we may finally learn how to age better, not just longer.

The study is published in the journal Engineering Open Access.

—–

Like what you read? Subscribe to our newsletter for engaging articles, exclusive content, and the latest updates. 

Check us out on EarthSnap, a free app brought to you by Eric Ralls and Earth.com.

—–