Research reveals AI eye checks can predict heart disease risk in less than a minute.Heart disease

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.

The world’s largest study of its kind reveals a breakthrough that will allow ophthalmologists and other healthcare professionals to perform high-street cardiovascular screening using cameras, without the need for blood tests or blood pressure checks. It may become possible.

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

The results, they say, could open the door to highly effective, non-invasive tests that don’t need to be done in a clinic for people at moderate to high risk of heart disease.

their discovery Published in the British Journal of Ophthalmology.

“This AI tool can tell you the level of risk within 60 seconds,” the study’s lead author, Professor Alicja Rudnicka, told the Guardian. If someone learns that their risk is higher than expected, they can prescribe a statin or offer another intervention.

Speaking at a health conference in Copenhagen, Rudnica, Professor of Statistical Epidemiology at St George’s University of London, added:

Cardiovascular disease, including cardiovascular disease, coronary heart disease, heart failure and stroke, is a leading cause of ill health and death worldwide. Cardiovascular disease alone is the most common cause of death worldwide. He accounts for one in four of his deaths in the UK alone.

Although some tests exist to predict risk, they are not always accurate in identifying people who will develop heart disease or die.

Researchers have developed a fully automated, AI-enabled tool, Quartz, to assess the feasibility of retinal vasculature imaging and known risk factors to predict vascular health and death.

They used the tool to scan images of 88,052 UK Biobank participants aged between 40 and 69. Researchers have developed predictive models for stroke, heart attack, and death, specifically looking at the width, vessel area, and tortuosity of retinal arteries and veins. from cardiovascular disease.

They then applied this model to retinal imaging of 7,411 participants aged 48 to 92 years from the European Prospective Cancer Investigation (Epic)-Norfolk study. Quartz’s performance was compared to the widely used Framingham risk score framework.

We tracked everyone’s health for an average of 7 to 9 years. In men, retinal vein and artery width, curvature and width change were found to be significant predictors of cardiovascular disease mortality. In women, changes in arterial area and width and venous curve and width contributed to risk prediction.

AI tools leveraged data from participants, including smoking history, high blood pressure medications, and previous heart attacks.

The researchers found that Quartz-calculated retinal data were significantly associated with cardiovascular disease, mortality, and stroke, showing predictive performance similar to Framingham’s clinical risk score.

“AI-enabled vascular instrumentation risk prediction is fully automated, low-cost, non-invasive, and does not depend on ‘high street’ availability and blood sampling or [blood pressure measurement] No need, ”writes the researcher.

in the linked editorialDr. Ify Mordi and Professor Emanuele Trucco of the University of Dundee, who were not involved in the study, said the idea of ​​AI checking heart health was “certainly attractive and intuitive.”

“This result reinforces evidence from several similar studies that the retina can be a useful and potentially disruptive source of cardiovascular disease risk in personalized medicine.”