Sign In

Communications of the ACM

ACM TechNews

AI-Enabled Eye Scan Delivers Stroke, Heart Disease Risk Scores

View as: Print Mobile App Share:
retinal scan representation

Retinal arteriolar and venular width, tortuosity, and area were extracted from 88,052 images.

Credit: Depositphotos

An artificial intelligence-enabled system developed by researchers in the U.K. can scan retinal images to identify individuals at high risk of heart disease and stroke. The Quartz (quantitative analysis of retinal vessels topology and size) system automatically detects minute differences in retinal vasculature.

In their study of more than 88,000 retinal images, the researchers found that the 10-year risk scores for stroke and heart disease produced by Quartz were on par with the commonly used Framingham Risk Score (FRS). The researchers say the automated AI-based system could monitor more people given that the FRS requires blood tests and blood pressure management.

The retinal images studied were from "non-expert personnel," and the researchers say better imaging from health care professionals could improve the results. They also indicated the potential for the technology to be deployed in a smartphone app.

From New Atlas
View Full Article


Abstracts Copyright © 2022 SmithBucklin, Washington, DC, USA


No entries found

Sign In for Full Access
» Forgot Password? » Create an ACM Web Account