Using eyes as a window, AI predicts annual heart attack risk from retinal scans

What if the information you need to assess your risk of a heart attack over the next year is in your eyes? Researchers led by the University of Leeds believe this to be true, and they have trained an artificial intelligence program to spot the warning signs.

The algorithm analyzes retinal scans taken during a routine visit to an ophthalmologist and looks for changes in the tiny blood vessels supplying the back of the eye, including complex patterns that have been linked to cardiovascular disease more large.

A team of engineers and clinicians from the UK, China, France, US and Belgium trained the AI ​​system on a collection of eye and heart scans collected from over 5,000 people . After being trained on both sets of data, the AI ​​program was able to use the retinal data to estimate the size and efficiency of the heart’s left ventricle, the workhorse responsible for pumping oxygenated blood to the rest of the body. body.

RELATED: Tesseract Raises $80 Million to Pursue a New Dimension of Eye Diagnostics

When combined with basic demographic statistics such as the patient’s age and gender, the AI ​​predicted their risk of having a heart attack in the next 12 months with between 70% and 80% accuracy. , the researchers said. Their findings were published in the journal Nature Machine Intelligence.

As an enlarged ventricle can be a major sign of impending heart disease, the researchers said their system could act as an important referral mechanism, screening patients during routine eye exams and recommending them for checkups. more in-depth cardiac procedures such as ultrasound or MRI.

RELATED: Using AI and dyes, new eye test spots glaucoma 18 months earlier in clinical study

Several companies are exploring the eyes as a window into a person’s health, as the cornea provides the only place where the body’s arteries, veins, and nerves can be viewed directly from the outside.

Last year, Tesseract raised $80 million for its diagnostics platform, which functions like a pair of high-tech binoculars pointed in the opposite direction. The scanner aims to detect not only eye diseases, but also heart and neurological conditions using a remote-controlled device.

Previously, the FDA granted one of its first AI-based diagnostic approvals to a diabetic retinopathy detection program with a retinal camera: the IDx-DR system, developed by Digital Diagnostics.

Comments are closed.