Retinal age gap as a predictive biomarker for mortality risk

Area of Science:

• Ophthalmology
• Gerontology
• Biomedical Engineering

Background:

• The aging process can be monitored using various biomarkers.
• Retinal fundus images offer a non-invasive window into physiological changes associated with aging.

Purpose of the Study:

• To develop a deep learning model for predicting chronological age from retinal fundus images, termed retinal age.
• To investigate the association between the retinal age gap and all-cause and cause-specific mortality risk.

Main Methods:

• A deep learning model was trained and validated using 19,200 fundus images from the UK Biobank.
• The model achieved a correlation of 0.81 between predicted retinal age and chronological age, with a mean absolute error of 3.55 years.
• Cox regression models analyzed the association between retinal age gap and mortality in 35,913 participants.

Main Results:

• Each year of increased retinal age gap was associated with a 2% higher risk of all-cause mortality.
• A 3% increased risk of non-cardiovascular and non-cancer mortality was observed for each year of increased retinal age gap.
• No significant association was found between retinal age gap and cardiovascular or cancer-related mortality.

Conclusions:

• The retinal age gap may serve as a novel biomarker for biological aging.
• Retinal images show potential as a screening tool for mortality risk stratification.
• This approach could facilitate personalized interventions for health risk management.