While the words “artificial intelligence” may immediately conjure up apocalyptic images of the fall of human civilization, there’s no doubt that A.I. has its less frightening benefits outside the world of science fiction.
Researchers from Google and Verily, the search engine’s health-tech arm, announced on Monday that they can use A.I. to figure out if someone has high blood pressure or is at risk of a heart attack or a stroke by simply scanning an individual’s eye, according to the Washington Post.
Researchers from Google trained an algorithm with more than 280,000 images of scanned retinas. The algorithm used the huge collection of data to train itself how to recognize patterns in people at risk for heart attacks.
The discovery is exciting considering one in four people in the U.S. die from heart disease, making it the country's leading cause of death according to the CDC. But the algorithm is not yet as efficient as current methods of detecting people at risk for heart conditions. The algorithm didn't outperform the accuracy of blood tests, but it was able to identify a person at risk 70 percent of the time. If the algorithm’s success rate grows and Google is able to fine-tune the technology, then it's possible that the method could become be a quicker and cheaper way to discover at-risk patients.
However, some don’t think Google’s new method would be necessary, even if it is improved. Maulik Majmudar, associate director of the Healthcare Transformation Lab at Massachusetts General Hospital, told the Washington Post that using Google’s algorithm would provide results that are only marginally different.
Google isn’t the only company trying to use A.I. to improve healthcare. Apple also launched a heart study linked to its Apple Watch, while London A.I. firm DeepMind is working to use similar algorithms to detect glaucoma and other eye diseases.