A tool artificialof eye-scanning intelligence can accurately predict a person's heart disease risk in less than a minute, researchers report.
The researchers developed a fully automated AI-enabled tool, the Quartz, to assess the potential of retinal vessel imaging – plus known risk factors – to predict vascular health.
They used the tool to scan pictures from 88.052 UK Biobank participants aged 40 to 69 years. The researchers specifically looked at the width, vessel area, and degree of curvature of arteries and veins in the retina to develop predictive models for stroke, heart attack, and death from circulatory disease.
They then applied the models to retinal images of 7.411 participants, aged 48 to 92, of the European Cancer Research Community (Epic)-Norfolk. Quartz's performance was compared to the widely used Framingham risk score framework.
Everyone's health was followed for an average of seven to nine years. In men, the width, curvature, and width variation of veins and arteries in their retinas were found to be significant predictors of death from circulatory disease.
In women, artery area and width, vein curvature, and width variation also contributed to predicting risk. The AI tool used data from participants, eg smoking history, taking medications for diabetes treatment of high blood pressure and previous heart attacks.
The researchers found that retinal data calculated by Quartz was significantly associated with cardiovascular disease, death and stroke.
Their findings were published in British Journal of Ophthalmology.