back Back

Deep-learning aging clock tracks human aging, detects eye and other diseases from retinal images

Apr. 04, 2023.
3 min. read 5 Interactions

"We are looking at aging through a different lens, bringing more information to the table."— Computational Biologist Dr. Sara Ahadi

About the Writer

Amara Angelica

174.42073 MPXR

Senior Editor Amara Angelica, an electrical engineer and inventor, was previously Editor of Kurzweil AI, working with Ray Kurzweil on The Singularity Is Near and other works

The fundus of the eye — the interior surface, including the retina and other features. It can be examined by ophthalmoscopy or special photography (credit: ignis).

A team of biomedical researchers has developed a non-invasive, more accurate, and inexpensive “aging clock” for tracking and slowing human aging by examining retinal images and using trained deep-learning models of the eye’s fundus (the deepest area of the eye), using a new “eyeAge” system.

The researchers are affiliated with Buck Institute for Research on Aging, Google Research, Google Health, Zuckerberg San Francisco General Hospital, Post Graduate Institute of Medical Education, and Research (India), and University of California, San Francisco.

Tracking eye changes that accompany aging and age-related diseases: the eyeAge system

The eyeAge system uses blood-vessel-rich tissue in the retina to identify 39 eye diseases, including glaucoma, diabetic retinopathy, and age-related macular degeneration (AMD), as well as non-eye diseases, such as chronic kidney disease and cardiovascular disease.

The researchers performed a genome-wide association study (GWAS) to establish the genetic basis to create the clock. Google researchers trained and tuned the eyeAGE model using their well-studied EyePACS data set  (involves more than 100,000 patients, with 5 million retinal images) and applied it to patients from the UK Biobank, based on data from more than 64,000 patients.

Slowing the aging process

“This type of imaging could be really valuable in tracking the efficacy of  interventions aimed at slowing the aging process,” says Pankaj Kapahi, a senior author of the study.

“The results suggest that potentially, in less than one year, we should be able to determine the trajectory of aging with 71% accuracy by noting discernable changes in the eyes of those being treated, providing an actionable evaluation of gero-protective therapeutics,” he said. 

Eye data likely more reliable than biomarkers from blood tests

Kapahi also noted that retinal scans are likely more reliable than blood tests because changes in the eye are less susceptible to day-to-day fluctuations, compared to biomarkers from the blood (which are more dynamic and can be influenced by something as simple as eating a meal or a current infection).

He also noted that subtle changes in small blood vessels often go undetected by even the most sophisticated instruments.

Making tracking aging more robust, powerful and comprehensive

“Our study emphasizes the value of longitudinal data for analyzing accurate aging trajectories,” adds co-corresponding author Sara Ahadi, a former Fellow at Google Research, and now Senior Computational Biologist at San Carlos, CA-based Alkahest, a clinical stage biopharmaceutical company targeting neurodegenerative and age-related diseases with transformative therapies. 

“Through EyePACS is a longitudinal dataset, involving multiple scans from individual people over time, our results show a more accurate positive prediction ratio for two consecutive visits of an individual, rather than random, time-matched individuals,” Ahadi says.

Looking at aging through a different lens

“The eyeAge is independent from phenotypic age [an aging clock based on blood markers],” Ahadi adds. “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.”

Citation: Ara Ahadiet et al. 2023. Longitudinal fundus imaging and its genome-wide association analysis provide evidence for a human retinal aging clock. eLife. DOI: (open access)

Interesting story? Please click on the 👍 button below!

Let us know your thoughts! Sign up for a Mindplex account now, join our Telegram, or follow us on Twitter

Comment on this content


0 thoughts on “Deep-learning aging clock tracks human aging, detects eye and other diseases from retinal images





💯 💘 😍 🎉 👏
🟨 😴 😡 🤮 💩

Here is where you pick your favorite article of the month. An article that collected the highest number of picks is dubbed "People's Choice". Our editors have their pick, and so do you. Read some of our other articles before you decide and click this button; you can only select one article every month.

People's Choice