AI Model Reveals True Biological Age From Five Drops of Blood

Some individuals seem to defy the effects of aging, appearing significantly younger than their peers despite sharing the same age. Aging isn't solely determined by the number of years we have lived; it's also influenced by genetics, lifestyle, and environmental factors. Conventional methods of assessing biological age typically focus on broad biomarkers, like DNA methylation or protein levels. However, these techniques often overlook the complex hormonal systems that regulate the body's internal balance. Now, scientists have developed a novel approach for estimating a person’s biological age, which measures how well the body has aged rather than simply counting the years since birth.

This new method, developed by scientists at Osaka University (Osaka, Japan), uses only five drops of blood to analyze 22 key steroids and their interactions, offering a more precise health assessment. Published in Science Advances, the team’s breakthrough study presents a potential leap forward in personalized health management, enabling earlier identification of age-related health risks and more tailored interventions. Since hormones are essential for maintaining bodily functions, the researchers chose to focus on these as key indicators of aging. To test this hypothesis, the team concentrated on steroid hormones, which are vital in metabolism, immune response, and stress management.

The researchers created a deep neural network (DNN) model that incorporates steroid metabolism pathways, making it the first AI model to consider the interactions between different steroid molecules. Rather than examining absolute steroid levels—which can vary greatly between individuals—the model looks at the ratios of steroids, delivering a more personalized and accurate biological age assessment. Trained on blood samples from hundreds of individuals, the model revealed that biological age differences become more pronounced as people age, an effect the researchers liken to a river widening as it flows downstream.

One of the most surprising findings of the study concerns cortisol, a steroid hormone linked to stress. The researchers discovered that when cortisol levels doubled, biological age increased by about 1.5 times. This suggests that chronic stress could speed up aging at the biochemical level, emphasizing the importance of managing stress to maintain long-term health. The team believes that this AI-driven biological age model could lead to more personalized health monitoring.

Potential future applications for this technology include early disease detection, tailored wellness programs, and lifestyle recommendations to slow the aging process. While the study marks significant progress, the team acknowledges that biological aging is influenced by numerous factors beyond hormones. With continued advancements in AI and biomedical research, the ability to measure—and possibly slow—biological aging is becoming more attainable. For now, the capability to assess an individual’s “aging speed” with a simple blood test could be a revolutionary development in preventive healthcare.

“This is just the beginning,” said Dr. Zi Wang, co-first and corresponding author of this work. “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.”

Related Links:
Osaka University

Visit expo >

Gold Member

Pharmacogenetics Panel

VeriDose Core Panel v2.0

Verification Panels for Assay Development & QC
Seroconversion Panels

New

Total Thyroxine Assay

Total Thyroxine CLIA Kit

New

Luteinizing Hormone Assay

DRG LH-Serum ELISA Kit