AI-based “tissue clocks” measure the biological age of human organs

Artificial intelligence-based “tissue clocks” can estimate the biological age of human organs from histological images, researchers at the CeMM Research Center for Molecular Medicine of the Austrian Academy of Sciences and the Ludwig Boltzmann Institute for Network Medicine (LBI-NetMed) at the University of Vienna have shown. By analyzing more than 25,000 tissue samples across 40 tissue types, their study revealed that organs age at different rates throughout life, and that these changes can be detected from blood samples. Results published in Natural medicine (DOI: 10.1038/s41591-026-04566-5), provides a new framework for understanding aging and may open new horizons for disease monitoring and early diagnosis.

Some people seem to age more slowly than others, looking and acting like they are 45 at 60. Others appear to be ahead of the calendar. But why does this happen, and what is actually happening inside the body? Is the lifespan of the liver different from that of the brain? Is it possible to measure the gap between the age in the passport and the biological age of each member?

By combining artificial intelligence with one of the world’s largest collections of human tissue images, a new study led by CeMM and LBI-NetMed principal investigator Andre Rendero and co-authored for the first time by Ernesto Abella, Eva Bolgan, and Yimin Zheng, takes a big step toward answering these questions. While previous studies have mainly focused on molecular changes such as DNA methylation or gene expression, the team is studying how the structure of the tissue itself changes over time.

A silent diary of time

To do this, the researchers turned to the Genotype and Tissue Expression (GTEx) project, which collected tissue samples from 983 individuals across 40 different tissue types, ranging from the brain and heart to the lung, pancreas, skin and intestine. They were converted into high-resolution digital images of tissue slices, each revealing the microstructure of the organ in question. The scale is staggering: 25,712 images, representing approximately 480 million individual images, analyzed using state-of-the-art vision models.

They found that organ structure keeps a silent diary of time: Even without explicitly teaching the AI ​​about it, age turned out to be the single strongest factor shaping tissue appearance across all 40 tissue types. Based on this, the research team developed so-called “tissue clocks” – predictive models that estimate a person’s biological age from the appearance of their tissues, for each organ independently.

These clocks achieved an average prediction error of only 4.9 years, and outperformed DNA-based aging estimates in capturing tissue-specific pathology. Importantly, biological life expectancy was strongly associated with hallmarks of aging, including telomere shortening, tissue pathology, and the number of chronic diseases an individual had.

Our tissues hold a remarkably detailed record of the aging process. By combining histological images with artificial intelligence, we can detect patterns of biological aging invisible to the human eye and begin to understand how aging manifests itself differently throughout the body.

Andre Rendero, principal investigator at CeMM and corresponding author of the study

Different schedule for each member

The analysis revealed that aging does not occur uniformly: some tissues, such as the lung, kidney, pancreas and adrenal gland, showed signs of accelerated aging already between the ages of 20 and 40. Other tissues followed more complex paths, with peaks of accelerated aging appearing later in life. The uterus showed a particularly striking transformation at menopause. Researchers have also identified strong links between tissue-specific aging and medical conditions or lifestyle factors. For example, kidney failure has been associated with accelerated aging signals in multiple tissues, while diabetes has shown pronounced effects in the pancreas.

“What stands out is how different the lifespan of each organ is, and how that manifests itself in the tissue structure,” says Ernesto Abela, co-first author of the study. “Deep learning allows us to read these spatial patterns, capturing aging as architectural redesign, not just molecular drift.” While tissue clocks recorded the natural pace of aging across organs, they also highlighted outliers – individuals whose tissues showed clear structural transformations before their chronological age.

However, tissue samples cannot always be collected. By correlating blood-based gene expression profiles with histologically derived tissue age gaps of the same individuals, researchers have constructed predictions of tissue-specific biological age from blood samples alone. “This is a conceptual leap: using the language of tissue aging, learned from images, and translating it into something that can be read from a routine blood draw,” explains co-first author Eva Bolgan.

Blood samples show aging patterns

These blood-based predictors have been successful in identifying patterns of aging associated with several diseases, including Alzheimer’s disease, Crohn’s disease, cystic fibrosis, vasculitis, diabetes, and stroke. In Alzheimer’s disease, for example, the strongest aging signal was detected specifically in the brain, while Crohn’s disease showed accelerated aging via the gastrointestinal tract.

“This study highlights that aging is not just a matter of time,” says Yimin Zheng, third co-first author of the study. “Different organs age in different ways, and these processes appear to be shaped by systemic and tissue-specific factors.” The results indicate that tissue architecture integrates many of the molecular and physiological changes associated with aging and disease. In the future, such approaches could contribute to minimally invasive diagnostics that monitor organ health and disease progression through blood tests.

The study also demonstrates the growing potential of artificial intelligence in pathology and aging research. By linking tissue imaging, gene expression and large-scale clinical data, the work provides a comprehensive view of how aging manifests itself throughout the human body.