Japanese scientists develop AI model to estimate biological age using blood test

Scientists at Osaka University in Japan have developed an advanced AI model capable of estimating a person’s biological age with remarkable precision. Unlike chronological age, which simply counts the years since birth, biological age reflects how well the body has aged internally.

This innovative method requires just five drops of blood to analyze 22 crucial steroids and their interactions, providing a comprehensive health assessment. Published in Science Advances, the study highlights the potential for early detection of age-related health risks and personalized health interventions.

Dr. Qiuyi Wang, co-first author of the study, explained the rationale behind the research: “Our bodies rely on hormones to maintain homeostasis, so we thought, why not use these as key indicators of aging?” The team specifically examined steroid hormones, which influence metabolism, immune response, and stress regulation.

To enhance accuracy, the researchers developed a deep neural network (DNN) model that incorporates steroid metabolism pathways—marking the first AI-driven approach that explicitly considers interactions between steroid molecules. One of the study’s most striking discoveries involved cortisol, a hormone linked to stress. The findings revealed that when cortisol levels doubled, biological age increased by approximately 1.5 times, suggesting that chronic stress significantly accelerates aging at a biochemical level.

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

The researchers believe their AI-powered biological age model could revolutionize personalized health monitoring. Potential future applications include early disease detection, customized wellness programs, and lifestyle recommendations designed to slow aging and improve overall health outcomes.

_{Images are for reference only.Images and contents gathered automatic from google or 3rd party sources.All rights on the images and contents are with their legal original owners.}