New AI Model to Estimate a Person's Biological Age

Using just five drops of blood, this new method analyses 22 key steroids and their interactions to provide a more precise health assessment.

Scientists at Osaka University in Japan have devised a new AI model to estimate a person’s biological age — a measure of how well their body has aged, rather than just counting the years since birth.

This new method, which uses just five drops of blood to analyse 22 key steroids and their interactions, provides a more precise health assessment. The team’s breakthrough study, published in Science Advances, offers a potential step forward in personalised health management, allowing for earlier detection of age-related health risks and tailored interventions.

“Our bodies rely on hormones to maintain homeostasis, so we thought, why not use these as key indicators of aging?” said Dr Qiuyi Wang, co-first author of the study.

To test this idea, the research team focused on steroid hormones, which play a crucial role in metabolism, immune function, and stress response. They collected blood samples from 130 individuals ranging in chronological age from 20 to 79 years old.

The team developed a deep neural network (DNN) model that incorporates steroid metabolism pathways, making it the first AI model to explicitly account for the interactions between different steroid molecules. This approach enabled the DNN to learn complex relationships between steroids and biological age.

One of the study’s most striking findings involves cortisol, a steroid hormone commonly associated with stress. The researchers found that when cortisol levels doubled, biological age increased by approximately 1.5 times.

This observation, supported by further analysis of steroid ratios and interaction terms, suggests that chronic stress could accelerate aging at a biochemical level, reinforcing the importance of stress management in maintaining long-term health.

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

The researchers are optimistic that this AI-powered biological age model could pave the way for more personalised health monitoring.

Future applications may include earlier disease detection, customised wellness programmes, and even lifestyle recommendations tailored to slow down aging.