New AI models can estimate biological age using blood samples

We all know someone who appears to be rebelling against the aged who appears younger than their peers despite their age. What is their secret? Scientists at Osaka University (Japan) may have found a way to quantify this difference. By incorporating hormonal (steroid) metabolic pathways into AI-driven models, they have developed a new system to estimate measures of how old the body is, rather than counting years from the time it is born.

Using just 5 drops of blood, this new method analyzes 22 important steroids and their interactions to provide a more accurate health assessment. The team's groundbreaking research has been published in Advances in scienceproviding a potential step in personalized health management, enabling early detection of age-related health risks and adjusted interventions.

Unlock aging signature on the body

Aging is shaped not only by years we have lived, but also by genetics, lifestyle and environmental factors. While traditional methods for estimating biological age rely on a wide range of biomarkers, such as DNA methylation and protein levels, these approaches often overlook complex hormonal networks that regulate the internal balance of the body.

Because our bodies rely on hormones to maintain homeostasis, why don't they use these as important indicators of aging? ”

Research co-author Dr. Qiuyi Wang

To test this idea, the researchers focused on steroid hormones. Steroid hormones play an important role in metabolism, immune function and stress response.

New AI-equipped model

The team developed a deep neural network (DNN) model that incorporates steroid metabolic pathways, becoming the first AI model to explicitly explain the interactions between different steroid molecules. Instead of looking at absolute steroid levels that can vary widely between individuals, the model examines steroid ratios and provides a more personalized and accurate assessment of biological age.

“Our approach reduces the noise caused by differences in individual steroid levels and allows the model to focus on meaningful patterns,” explains Dr. Zi Wang, co-first and corresponding author of the work. The model was trained on blood samples from hundreds of individuals and revealed that biological age differences tend to spread as they age.

Important insights and meanings

One of the most prominent findings of the study is cortisol, a steroid hormone commonly associated with stress. Researchers found that when cortisol levels doubled, biological age increases by about 1.5 times. This suggests that chronic stress can accelerate aging at biochemical levels and enhance the importance of stress management in maintaining long-term health.

“Stress is often commonly discussed, but our findings provide concrete evidence that it has a measurable effect on biological aging,” says corresponding author, Professor Toshifumi Toshifumi Takao, an expert on analytical chemistry and mass spectrometry.

Researchers believe that the AI-powered biological age model could pave the way for more personalized health surveillance. Future applications may include early disease detection, customized wellness programs, and even lifestyle recommendations tailored to slow aging.

Looking ahead

While this research represents a major advance, the team acknowledges that biological aging is a complex process that is influenced by many factors other than hormonals. “This is just the beginning,” says Dr. Z. Wang. “We hope to expand our dataset and incorporate additional biological markers to further improve our models and unlock deeper insights into the mechanisms of aging.”

Ongoing advances in AI and biomedical research have made it even more possible to achieve accurate measurements and even aging of lowered toxicology. For now, however, the ability to assess “rate of aging” with simple blood tests could mark game-changing developments in preventive medicine.