Seoul National University researchers develop AI retina scan to detect biological aging

Researchers at Seoul National University have developed an artificial intelligence-powered retina scanning method capable of determining an individual's biological aging rate and identifying hidden systemic health risks. The AI system, trained on approximately 30,000 retina scans and tested on 15,000 others, can predict a person's chronological age with an error margin of only 2.5 to 2.7 years.

The study identified a ‘Retina Age Gap’ between a person's actual age and the biological age indicated by their eyes, which correlates directly with lifestyle and chronic conditions. Findings show that the retinas of diabetic patients appear, on average, 2.52 years older than their chronological age. Additionally, smoking adds approximately half a year to the retinal age, while macular degeneration adds about 0.6 years.

Because the retina's vascular structure is directly linked to the brain and cardiovascular system, experts suggest this technology could be integrated into routine eye examinations. This could serve as a practical biological indicator for the early diagnosis of cardiovascular risks and systemic internal diseases before clinical symptoms appear.