AI eye checks can predict heart disease
|Photograph: Zorica Nastasic/Getty Images|
From The Guardian
An artificial intelligence tool that scans eyes can accurately predict a person’s risk of heart disease in less than a minute, researchers say.
The breakthrough could enable ophthalmologists and other health workers to carry out cardiovascular screening on the high street using a camera – without the need for blood tests or blood pressure checks – according to the world’s largest study of its kind.
Researchers found AI-enabled imaging of the retina’s veins and arteries can specify the risk of cardiovascular disease, cardiovascular death and stroke.
They say the results could open the door to a highly effective, non-invasive test becoming available for people at medium to high risk of heart disease that does not have to be done in a clinic.
Their findings were published in the British Journal of Ophthalmology.
“This AI tool could let someone know in 60 seconds or less their level of risk,” the lead author of the study, Prof Alicja Rudnicka, told the Guardian. If someone learned their risk was higher than expected, they could be prescribed statins or offered another intervention, she said.
Speaking from a health conference in Copenhagen, Rudnicka, a professor of statistical epidemiology at St George’s, University of London, added: “It could end up improving cardiovascular health and save lives.”
Circulatory diseases, including cardiovascular disease, coronary heart disease, heart failure and stroke, are major causes of ill health and death worldwide. Cardiovascular disease alone is the most common cause of death globally. It accounts for one in four deaths in the UK alone.
While several tests to predict risk exist, they are not always able to accurately identify those who will go on to develop or die of heart disease.
Researchers developed a fully automated AI-enabled tool, Quartz, to assess the potential of retinal vasculature imaging – plus known risk factors – to predict vascular health and death.
They used the tool to scan images from 88,052 UK Biobank participants aged 40 to 69. The researchers looked specifically at the width, vessel area and degree of curviness of the arteries and veins in the retina to develop prediction models for stroke, heart attack and death from circulatory disease.
Everyone’s health was tracked for an average of seven to nine years. In men, the width, curviness and width variation of veins and arteries in their retinas were found to be important predictors of death from circulatory disease. In women, artery area and width and vein curviness and width variation contributed to risk prediction.
The AI tool harnessed data from participants including any history of smoking, drugs to treat high blood pressure, and previous heart attacks.
Researchers found the retina data computed by Quartz was significantly associated with cardiovascular disease, deaths and strokes, with similar predictive performance to the Framingham clinical risk score.
“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,” the researchers wrote.