Retinal imaging model predicts age and reveals sex differences in human aging
The retinal age gap correlates with mortality, disease risks, and sex-specific genetic pathways in more than 71,000 UK Biobank participants.
Nature communications · Trofimova O et al. · Paper published 26 Aug 2026
Researchers analyzed retinal fundus images from 71,343 human participants in the UK Biobank. They fine-tuned the deep learning foundation model RETFound to predict chronological age, reaching a mean absolute error of 2.85 years. The retinal age gap, defined as the difference between predicted and actual age, tracked with inflammation, cardiometabolic traits, cognitive performance, all-cause mortality, dementia, cancer, and incident cardiovascular disease. Genome-wide analyses linked this gap to genes involved in longevity, metabolism, neurodegeneration, and eye diseases. Sex-stratified analyses revealed distinct biological features. Retinal aging in males showed stronger ties to metabolic syndrome. In females, retinal aging involved vascular pathways and shifted across menopause, with postmenopausal women displaying higher age gaps and clinical profiles resembling those in males.
Why it matters
The findings indicate that non-invasive retinal imaging captures systemic aging processes and age-related disease risks. They also show that aging trajectories differ biologically between men and women.
Caveats
The study relied on observational data from a single cohort, the UK Biobank. It evaluated associations without directly demonstrating causal biological mechanisms.
Written from the paper’s abstract, and every claim checked against it before publishing. Read the paper for the full methods and data.
The paper
Deep learning aging marker from retinal images unveils sex-specific clinical and genetic signatures
Trofimova O, Böttger L, Bors S et al.
Nature communications · 26 Aug 2026 · Peer-reviewed
- Relevance
- Core geroscience
- News value
- Important
- Evidence
- Humans
- Status
- Peer-reviewed
More on Aging clocks
See allBiological age uncertainty independently predicts mortality and health decline in humans
Researchers derived biological age uncertainty across UK Biobank participants, finding that higher uncertainty reflects reduced physiological coherence and predicts worse health outcomes.
medRxiv · Li Y et al.
Organ age acceleration and mortality risk reflect distinct biological processes
Multi-omics clocks across fourteen organs reveal divergent molecular programs and uncover thirteen candidate genes separating age acceleration from mortality.
Research Square · Na R et al.
Blood cell composition explains substantial variation in DNA methylation age
Cell counts explain less variation in age acceleration and only modestly affect its links to mortality and 176 incident health outcomes.
Genome medicine · Jonkman TH et al.
Kidney tubular epithelial cells drive accelerated epigenetic aging in disease
A cross-species single-cell atlas links injured human kidney cells and aged mouse kidneys to shared chromatin reorganization and impaired repair.
Nature aging · Jeong H et al.
Chronological age prediction does not prove biological age measurement
Researchers show that standard age-trained clocks reflect task-specific statistics rather than true biological aging constructs, limiting how researchers interpret clock gaps and rejuvenation.
bioRxiv · Song S et al.