Tissue clocks from histopathology images in 983 GTEx donors
In the Genotype-Tissue Expression cohort, deep learning on 25,712 histopathology images from 40 tissue types in 983 individuals produced 'tissue clocks' predicting biological age; tissue-specific age acceleration was associated with demographic, lifestyle and medical factors. [1]
Automatic summary · not editorially reviewed
The key findings
The analysis used 25,712 whole-slide histopathological images from 40 tissue types across 983 individuals in the Genotype-Tissue Expression cohort. [1]
Tissue-specific age acceleration was associated with demographic, lifestyle and medical factors described as potentially modifiable. [1]
The blood-based approach was reported as validated across independent cohorts for eight prevalent diseases, including Alzheimer's disease, stroke and Crohn's disease. [1]
The source at a glance
- Study type / format
- Abstract of a histopathology imaging study using deep learning
- Population / context
- 983 individuals in the Genotype-Tissue Expression cohort, across 40 tissue types
- Summary based on
- Study abstract
- Original publication
- August 14, 2026
GTEx histology images across 40 tissue types
The abstract describes a comprehensive assessment of age-related structural and architectural remodeling of human tissues. It used 25,712 whole-slide histopathological images from 40 tissue types across 983 individuals in the Genotype-Tissue Expression cohort. Deep learning was used to quantify morphological alterations and build 'tissue clocks', described as predictors of biological age reflecting tissue structural integrity and physiological fitness.
Supporting source [1]
Correlations and factors linked to tissue age gaps
The clocks correlated with established aging markers such as telomere attrition, subclinical pathologies and comorbidities. A systematic evaluation of biological aging rates across organs identified associations of tissue-specific age acceleration with demographic, lifestyle and medical factors, described as potentially modifiable risk factors affecting tissue aging. These are associations, not demonstrated causes.
Supporting source [1]
Blood-based prediction validated in eight diseases
By integrating paired histology and transcriptomic data, the authors developed a strategy to predict tissue-specific age gaps directly from blood samples. They report validating this approach by identifying disease-relevant organ aging across independent cohorts for eight prevalent diseases, including Alzheimer's disease, stroke and Crohn's disease. The abstract does not report effect sizes, cohort sizes or the strength of these predictions.
Supporting source [1]
How to interpret this
This is an abstract; the full text was not reviewed. The abstract reports no effect sizes, cohort sizes for the validation, follow-up or predictive accuracy, and the reported factor links are associations, not causes.
Based on the study abstract; the full paper, tables and supplementary data were not reviewed.
Source & supporting passages
Abila E, Buljan I, Zheng Y, Kleissl L, Klotz S, Veres T, Weng Z, Nackenhorst M, Kamies R, Michl A, Kadri S, Moustafa S, Hulla W, Perkonigg M, Drach M, Tschandl P, Sterniczky B, Heinig M, De Sadeleer LJ, Wuyts W, Vanaudenaerde B, Ceulemans LJ, Buchanan DD, Fennell LJ, Stary G, Tolkach Y, Wöhrer A, Schiller HB, Rendeiro AF. · europepmc.org · August 14, 2026