Google researchers are testing an artificial intelligence (AI) platform that aims to predict a person’s risk of heart attack or stroke by examining images of the patient’s retina. They hope this method can eventually replace more invasive techniques for predicting cardiovascular disease.

Using these eye images and deep-learning models, the researchers were able to predict cardiovascular risk factors such as age (mean error within 3.26 years), systolic blood pressure (mean error within 11.23 mm Hg) and smoking status (71 percent predictive accuracy). And with 70 percent accuracy, they were able to determine which individuals would have a major adverse cardiac event within five years.

These findings were published Feb. 19 in Nature Biomedical Engineering.

The researchers’ technique involved creating a graphical representation of which pixels in an image were most important for identifying certain risk factors. But it needs to be validated with more data sets other than the groups of 12,026 and 999 patients used in the initial study, lead researcher Lily Peng told USA Today.

"Pattern recognition and making use of images is one of the best areas for AI right now,” Harlan M. Krumholz, MD, a professor of medicine and director of Yale’s Center for Outcomes Research and Evaluation, told the newspaper.

“[It will] help us understand these processes and diagnoses in ways that we haven't been able to do before," Krumholz said. "And this is going to come from photographs and sensors and a whole range of devices that will help us essentially improve the physical examination and I think more precisely hone our understanding of disease and individuals and pair it with treatments."

Read the full story below: