0
0
OSAKA, JAPAN – Scientists at Osaka University have unveiled a revolutionary AI model capable of estimating a person’s biological age with remarkable accuracy using just five drops of blood. This groundbreaking development, published in Science Advances, promises to transform personalized health management by providing a deeper understanding of how our bodies age beyond the simple passage of years.
We all know individuals who seem to age gracefully, defying their chronological age. Now, researchers have developed a method to quantify this phenomenon by analyzing 22 key steroids and their interactions, offering a more precise health assessment than traditional age measurements.
“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.
The team focused on steroid hormones, vital for metabolism, immune function, and stress response, and developed a deep neural network (DNN) model that incorporates steroid metabolism pathways. This AI model is the first to explicitly account for the complex interactions between different steroid molecules. Instead of focusing on absolute steroid levels, which vary significantly between individuals, the model analyzes steroid ratios, providing a more personalized and accurate assessment.
“Our approach reduces the noise caused by individual steroid level differences and allows the model to focus on meaningful patterns,” explained Dr. Zi Wang, co-first and corresponding author.
The model, trained on blood samples from hundreds of individuals, revealed that biological age differences tend to widen with age, akin to a river expanding downstream. Notably, the study found that a doubling of cortisol levels, a hormone linked to stress, increased biological age by approximately 1.5 times. This suggests that chronic stress can accelerate 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,” said Professor Toshifumi Takao, a corresponding author and expert in analytical chemistry and mass spectrometry.
The researchers believe this AI-powered model could pave the way for personalized health monitoring, enabling early disease detection, tailored wellness programs, and lifestyle recommendations to slow aging.
While the study marks a significant advancement, the team acknowledges that biological aging is multifaceted. “This is just the beginning,” said Dr. Z. Wang. “By expanding our dataset and incorporating additional biological markers, we hope to refine the model further and unlock deeper insights into the mechanisms of aging.”
With ongoing advancements in AI and biomedical research, the ability to accurately measure and potentially slow biological aging is becoming increasingly feasible.
More information: Toshifumi Takao et al, Biological age prediction using a DNN model based on pathways of steroidogenesis, Science Advances (2025). DOI: 10.1126/sciadv.adt2624. www.science.org/doi/10.1126/sciadv.adt2624
Journal information: Science Advances
Disclaimer: This article is based on the provided information and should not be taken as medical advice. The AI model described is still under development, and further research is needed to validate its accuracy and clinical applications. Consult with a healthcare professional for any health-related concerns. The results of this study are preliminary, and future research may yield differing results.
