Scientists in Austria have developed a new method to estimate the biological age of human organs based on histological images. Published today in Nature Medicine, their findings could pave the way for blood tests capable of monitoring aging and disease across the entire human body.
“Our tissues carry a remarkably detailed record of the aging process,” said André Rendeiro, PhD, principal investigator at the Research Center for Molecular Medicine of the Austrian Academy of Sciences (CeMM) and senior author of the study. “By combining histology images with artificial intelligence, we can detect patterns of biological aging that are invisible to the human eye and begin to understand how aging unfolds differently across the body.”
While previous studies have largely focused on the molecular changes associated with aging, Rendeiro’s team took a different approach, using AI to examine how tissue architecture changes over time. The researchers analyzed more than 25,000 high-resolution histological images from the Genotype-Tissue Expression Project (GTEx), spanning 40 different types of tissues.
Age emerged as the strongest factor defining tissue structure across all 40 tissue types. Based on these results, the team developed predictive models that could estimate the biological age of individual tissues. These “tissue clocks” achieved a mean error of 4.9 years, outperforming existing DNA-based aging estimates.
The analysis revealed that aging is not uniform across tissues. While organs like the lungs, kidneys, pancreas, and adrenal gland already showed signs of aging between the ages of 20 and 40, other organs, like the uterus, followed more complex trajectories with peaks of accelerated aging later in life.
“What stands out is how differently each organ ages, and how that shows up in tissue architecture,” said Ernesto Abila, biomedical data scientist at CeMM and co-first author of the study. “Deep learning lets us read these spatial patterns, capturing aging as architectural remodeling, not just molecular drift.”
Because of the invasive nature of biopsies, many organs cannot be routinely sampled in clinical practice. To address this limitation, the researchers linked the changes captured by the tissue clocks with gene expression profiles measured through blood tests. These blood-based predictors reproduced aging signatures associated with several conditions, including Alzheimer’s disease, Crohn’s disease, cystic fibrosis, vasculitis, diabetes and stroke.
“This is a conceptual leap: using the language of tissue aging, learned from images, and translating it into something readable from a routine blood draw,” said Iva Buljan, doctoral researcher at CeMM and co-first author of the study.
The findings suggest that tissue architecture integrates key features of both molecular and physiological aging, capturing the broader picture of complex aging processes throughout the human body. With further validation, this approach could support minimally invasive methods to monitor organ-specific aging and disease progression.
“This study highlights that aging is not simply a matter of chronological time,” said Yimin Zheng, PhD, postdoctoral fellow at CeMM and co-first author of the study. “Different organs age in different ways, and these processes appear to be shaped by both systemic and tissue-specific factors.”
