Google Algorithms Use Retinal Images to Predict Heart Disease Risk
A new study involves images from 280K+ people.
Algorithms developed by Google maybe be helpful in identifying heart disease risk, researchers have found.
The American Optometric Association writes that for a new study published in the journal Nature Biomedical Engineering, researchers relied on retinal fundus images from more than 280,000 people. They "were able to make the link to cardiovascular disease and predict 70 percent of the time which patients were likely to have a heart attack within five years," according to AOA.
The Google researchers write: "In this work, we demonstrate the extraction and quantification of multiple cardiovascular risk factors from retinal images using deep learning."
The researchers' approach is "impressive" in its ability to subtle changes in the eye that might otherwise be hard to spot, says Dr. Paul Barney, chairman of the AOA's New Technologies Committee.
He states, "The technology could be used positively. It could create a gateway for people to see their doctor of optometry for a comprehensive eye examination, explain the risk factors for cardiovascular disease and orchestrate the care that they need. The earlier the symptoms are detected, the better."