Graphic of an artificial eye

AI discovers new cause of high blood pressure

Image credit: Dreamstime

Artificial intelligence (AI) has found that twisting of eye vessels could cause high blood pressure and heart disease, scientists have said.

A team of scientists at St George’s, University of London, used artificial intelligence tools to analyse the blood vessels found at the back of the eye and their connection with heart diseases. 

The team discovered 119 areas in the genome (complete set of DNA) that help to determine the size and shape of these vessels and which could be used in routine eye checkups to help identify health problems. 

In the past, scientists have shown that the shape and size of blood vessels on the retina are associated with health conditions including high blood pressure, heart disease, diabetes and obesity.

However, until now, little was known about how genetics play a role in determining the architectural characteristics of these blood vessels.

The researchers found that an increase in ‘twisting’ of the arteries could be a key element in the development of these conditions. 

The team studied retinal images from nearly 53,000 people who were enrolled on a large study called the UK Biobank. The scientists applied AI technology to the images to quickly and automatically distinguish between the different types of blood vessels (arteries and veins) and to measure blood vessel width and the extent to which the vessels twist and turn.

The team then used a technique called a genome-wide association study (GWAS) to determine whether there were similarities in the DNA of people with similar blood vessel characteristics. 

The researchers then repeated the analyses on 5,000 people who were part of the EPIC-Norfolk’s Eye Study. 

Of the 119 sections found, 89 regions were linked to arterial twisting.

“It had been thought that high blood pressure might cause twisted arteries, but our work unveils that it’s actually the other way around," said Professor Christopher Owen, head of chronic disease epidemiology at St George’s, University of London. 

"This genetic information is a vital piece of the puzzle in our understanding and could pave the way for new treatments in the future.

“Our AI analysis of these images as part of routine eye checks could easily be done as part of a health check to identify those at high risk of developing high blood pressure or heart disease and in need of early intervention.”

The study, funded by the Medical Research Council and the British Heart Foundation, was published in PLOS Genetics.

Sign up to the E&T News e-mail to get great stories like this delivered to your inbox every day.

Recent articles