LONDON —A simple eye test that measures the veins and arteries in the retina can predict death from cardiovascular disease, a new study reveals.
The test combines artificial intelligence (AI) with scans of the retina, a membrane at the back of the eyes that contains light sensitive cells. The technique could lead to a screening program, allowing doctors to prescribe drugs and lifestyle changes decades before heart disease symptoms emerge.
Lead author Professor Alicja Regina Rudnicka from St. George’s University of London says this test is inexpensive, accessible, and non-invasive. People at risk of stroke, heart attack, and other circulatory conditions could undergo RV (artificial intelligence enabled retinal vasculometry) during routine visits to their optometrist.
“AI-enabled vasculometry risk prediction is fully automated, low cost, non-invasive and has the potential for reaching a higher proportion of the population in the community because of ‘high street’ availability and because blood sampling or [blood pressure measurement] are not needed,” researchers say in a media release.
Study authors add that the procedure is highly likely to help prolong the disease-free status of aging adults with increasing comorbidities and assist in minimizing healthcare costs tied to heart disease.
How does the test work?
Researchers developed an algorithm called QUARTZ, based on retinal images from tens of thousands of adults between 40 and 69 years-old. It focused on the width, area, and curvature (or tortuosity) of tiny blood vessels called arterioles and venules. The team compared the performance of QUARTZ with the widely used Framingham Risk Scores framework – both separately and jointly.
They tracked the health of all the participants for an average of seven to nine years, during which time there were 327 and 201 circulatory disease deaths among 64,144 UK Biobank and 5,862 EPIC-Norfolk participants, respectively. In men, arteriolar and venular width, tortuosity, and width variation emerged as important predictors of death from circulatory disease. In women, arteriolar and venular area and width and venular tortuosity and width variation contributed to risk prediction.
The predictive impact of retinal vasculature on circulatory disease death interacted with smoking, high blood pressure drugs, and heart attack history. Overall, these predictive models, based on age, smoking, medical history, and retinal vasculature, captured between half and two-thirds of circulatory disease deaths in those most at risk.
Retinal vasculature models captured about five percent more cases of stroke in UK Biobank men, eight percent more cases in UK Biobank women, three percent more cases among EPIC-Norfolk men most at risk, and nearly two percent fewer cases among EPIC-Norfolk women.
Framingham Risk Scores captured more cases of heart attack among those most at risk. Retinal imaging is already common practice in the U.K. and the U.S., the researchers point out.
“[Retinal vasculature] is a microvascular marker, hence offers better prediction for circulatory mortality and stroke compared with [heart attack] which is more macrovascular, except perhaps in women,” the team explains.
“In the general population it could be used as a non-contact form of systemic vascular health check, to triage those at medium-high risk of circulatory mortality for further clinical risk assessment and appropriate intervention.”
Dr. Ify Mordi and Dr. Emanuele Trucco, of the University of Dundee, who did not take part in the study, say the use of retinal vasculature changes to inform overall cardiovascular risk is “certainly attractive and intuitive.”
“Using retinal screening in this way would presumably require a significant increase in the number of ophthalmologists or otherwise trained assessors,” the researchers conclude.
“What is now needed is for ophthalmologists, cardiologists, primary care physicians and computer scientists to work together to design studies to determine whether using this information improves clinical outcome, and, if so, to work with regulatory bodies, scientific societies and healthcare systems to optimize clinical workflows and enable practical implementation in routine practice.”