The old expression is that eyes are the window into the soul. However, new research says they are the window to age. The research was a collaboration between the Buck Institute for Research on Aging, Zuckerberg San Francisco General Hospital Google Research.
Aging clocks use biomarkers to determine people’s biological age and predict mortality. It usually requires blood work and can be invasive. This new method, called eyeAge, instead tracks changes in the retina’s microvasculature to look for signs of blood sugar-related retinopathy, Parkinson’s, Alzheimer’s, AIDS, hypertension and tumors. While biomarkers fluctuate with meals, infections and other factors, retina scans don’t have day-to-day fluctuations.
Sara Ahadi, a senior co-author of the study, said, “In less than one year we should be able to determine the trajectory of aging with 71 percent accuracy by noting discernible changes in the eyes.”
Google worked to develop AI that analyzes images of the eye to monitor specific criteria. This is a fast, cost-efficient way of tracking eye changes. The only drawback is that analyzing images of eyes is currently too complicated for even excellent clinicians. This won’t be a method doctors use by looking at images of eyes on their own. However, the researchers have released the code here.
The AI was trained on images from more than 100,000 patients to learn what to look for. It has been tested on more than 64,000 patients.
“Our study emphasizes the value of longitudinal data for analyzing accurate aging trajectories. [By using] multiple scans from individual people over time our results show a more accurate positive prediction ratio for two consecutive visits of individual rather than random, time-matched individuals,” said Sara Ahadi. “We are looking at aging through a different lens and bringing more information to the table. We hope eyeAge will be utilized along with other clocks to make tracking aging more robust, powerful and comprehensive.”
Having multiple ways to monitor the potential development of health concerns and the progression of conditions is essential. Current methods are invasive and expensive. Having cheap, fast methods on hand would be a boon. However, we are left with the question of who will take pictures of the patient’s eye. A clear closeup of a retina can’t be easy to capture. However, this may be the future diagnostic tool once they clear that hurdle.
