The Faculty of Medicine

Your DNA Knows Your Age: Hebrew University Researchers Develop a Blood Test That Accurately Predicts Chronological Age

Researchers from the Faculty of Medicine and the School of Computer Science and Engineering at the Hebrew University of Jerusalem have developed a deep learning model that can accurately predict a person’s chronological age based on a simple blood sample.

The model relies on DNA methylation patterns—chemical modifications that occur naturally over time—and was developed by graduate students Bracha Ohana and Daniel Nudelman, under the supervision of Professors Ruth Shemer, Yuval Dor, and Tommy Kaplan.

The study found that changes in DNA methylation accumulate in a consistent and predictable manner throughout life, enabling the model to estimate age with a remarkable median accuracy of just 1.5 years.

These findings suggest that aging is not entirely a random process but may be governed by a biological mechanism that senses the passage of time. The research also raises intriguing questions about how organs age: does every cell in a tissue age gradually, or do tissues consist of a dynamic mix of young and old cells, with proportions that shift over time?

Photo: Nir Friedman