AI eye checks can predict heart disease risk in less than a minute, study finds

An artificial intelligence tool that scans the eyes can accurately predict a person’s risk of heart disease in less than a minute, researchers say.

Breakthrough could allow ophthalmologists and other healthcare workers to perform high street cardiovascular screening using a camera – without the need for blood tests or blood pressure checks – according to the largest study in the world. kind in the world.

Researchers have found that AI-enabled imaging of retinal veins and arteries can pinpoint the risk of cardiovascular disease, cardiovascular death, and stroke.

They say the results could open the door to a highly effective, non-invasive test available to people at medium to high risk of heart disease that doesn’t have to be done in a clinic.

Their findings were published in the British Journal of Ophthalmology.

“This AI tool could inform someone in 60 seconds or less of their level of risk,” the study’s lead author, Professor Alicja Rudnicka, told The Guardian. If someone learned their risk was higher than expected, they could be prescribed statins or offered another procedure, she said.

Speaking at a health conference in Copenhagen, Rudnicka, professor of statistical epidemiology at St George’s, University of London, added: “It could end up improving cardiovascular health and saving lives.”

Circulatory diseases, including cardiovascular disease, coronary heart disease, heart failure and stroke, are the leading causes of ill health and death worldwide. Cardiovascular disease alone is the most common cause of death worldwide. It accounts for one in four deaths in the UK alone.

Although there are several tests to predict risk, they are not always able to accurately identify those who will develop or die from heart disease.

Researchers developed a fully automated AI-based tool, Quartz, to assess the potential of retinal vascular imaging – along with known risk factors – to predict vascular health and death.

They used the tool to scan images of 88,052 UK biobank participants aged 40 to 69. Researchers looked specifically at the width, vessel area, and degree of curvature of retinal arteries and veins to develop predictive models for strokes, heart attacks, and death. of a circulatory disease.

They then applied the models to retinal images of 7,411 participants, aged 48 to 92, from the European Prospective Cancer Study (Epic)-Norfolk. The performance of Quartz was compared to the widely used Framingham risk scoring framework.

Everyone’s health was tracked for an average of seven to nine years. In men, the width, curvature and variation in width of veins and arteries in their retinas have been shown to be strong predictors of death from circulatory disease. In women, the area and width of arteries and the curvature and variation in width of veins contributed to the prediction of risk.

The AI ​​tool mined participants’ data, including smoking history, medications to treat high blood pressure and previous heart attacks.

Researchers found that retinal data calculated by Quartz was significantly associated with cardiovascular disease, death, and stroke, with predictive performance similar to the Framingham clinical risk score.

“AI-based vasculometry risk prediction is fully automated, inexpensive, non-invasive, and has the potential to reach a higher proportion of the population in the community due to high street availability and because blood samples or [blood pressure measurement] are not necessary,” the researchers wrote.

In a linked editorial, Dr Ify Mordi and Professor Emanuele Trucco, from the University of Dundee, who were not involved in the study, said the idea of ​​AI eye checks for heart health was ” certainly attractive and intuitive”.

They added: “The findings reinforce evidence from several similar studies that the retina may be a useful and potentially disruptive source of information for CVD risk in personalized medicine.”

#eye #checks #predict #heart #disease #risk #minute #study #finds

Leave a Comment

Your email address will not be published. Required fields are marked *