Researchers have discovered a simple eye test that can be used to diagnose heart disease with the help of artificial intelligence (AI).
According to the World Health Organization (WHO), heart disease is the leading cause of death globally, with an estimated 17.9 million people dying from this condition each year.
WHO states that early detection of heart disease, which often leads to heart attacks, can provide patients with valuable time for treatment, potentially saving many lives.
Previous research has explored how the venous and arterial systems of the retina can provide early signs of heart disease.
This study examined how the width of these blood vessels could be used to predict heart disease, but it was unclear whether the findings applied equally to men and women.
Researchers at St George’s, University of London, utilized an AI model to analyze data from patients in two studies in the UK and Europe to predict the future risk of cardiovascular disease.
They developed a fully automated AI-assisted algorithm called QUARTZ (Qualitative Analysis of Retinal Vessel Structure and Size) to predict cardiovascular health and mortality based on retinal imaging.
The new algorithm helps predict cardiovascular health and mortality based on retinal imaging. (Photo: Adobe Stock).
Using retinal images from 88,052 participants in the UK Biobank aged 40 to 69, QUARTZ first specifically examined the width, area of blood vessels, and the curvature (or tortuosity) of arterioles and venules in the retina to develop predictive models for strokes, heart attacks, and deaths from circulatory diseases.
They then applied this model to retinal images of 7,411 participants aged 48 to 92 from the European Prospective Investigation into Cancer (EPIC) Norfolk study.
The health of all participants was monitored over an average period of 7 to 9 years, during which there were 327 deaths due to cardiovascular disease among 64,144 UK Biobank participants and 201 deaths from circulatory conditions among 5,862 EPIC-Norfolk participants.
Overall, these predictive models, based on age, smoking status, medical history, and retinal blood vessels, captured between half to two-thirds of circulatory disease deaths in the highest risk individuals.
The results of QUARTZ were compared with the Framingham Score, a tool currently widely used to predict heart disease risk based on health data.
