AI can predict future fatal heart attacks by eyes testing

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 the disease each year.

The WHO says that early detection of heart disease, which often leads to heart attacks, can give patients more time to get treatment, saving lives.

Previous research has explored how the retina’s venous and arterial systems can provide early signs of heart disease.

That study looked at how the width of these blood vessels could be used to predict heart disease, but it’s not clear if the findings apply equally to men and women.

Researchers at St George’s, University of London, used an AI model to study a database of patients from two studies in the UK and Europe to predict future cardiovascular disease risk. They developed a fully automated AI-powered algorithm called QUARTZ (or Retinal Vessel Topology Analysis and siZe) to predict cardiovascular health and mortality from retinal imaging.

Using retinal images from 88,052 UK Biobank participants aged 40 – 69, QUARTZ first looked specifically at the width, area of blood vessels and the degree of curvature (or curvature) of the arterioles and veins in the retina to develop predictive models of stroke, heart attack, and death from circulatory disease.

They then applied this model to retinal images of 7,411 participants aged 48-92 from the second European Prospective Inquiry on Cancer (EPIC) Norfolk study.

The health of all participants was followed for an average of 7 to 9 years. During that time there were 327 deaths from cardiovascular disease out of 64,144 Biobank participants in the UK. There were 201 circulatory disease deaths among the 5,862 EPIC-Norfolk participants.

Collectively, these predictive models, based on age, smoking, medical history, and retinal vascularity, captured between half and two-thirds of circulatory disease deaths in individuals with highest risk.

The QUARTZ results were compared with the Framingham Scale, a widely used tool to predict heart disease risk based on health data.