Scientists from Google and its subsidiary Verily have analysed scans of the back of a patient’s eye to predict their risk of suffering a heart attack.
This algorithm could make it quicker for doctors to analyse a patient’s risk as it does not require a blood test.
The reason the eye is so important for research is that the rear interior wall of the eye is full of blood vessels which can be used to judge a person’s overall health.
Doctors are able to gather information such as blood pressure, their age and whether they smoke, which are all important in determining someone’s cardiovascular health.
A paper describing the work has been published in the Nature journal Biomedical Engineering.
Luke Oakden-Rayner, a medical researcher at the University of Adelaide who specializes in machine learning analysis, told The Verge: “They’re taking data that’s been captured for one clinical reason and getting more out of it than we currently do.
“Rather than replacing doctors, it’s trying to extend what we can actually do.”
The scientists used machine learning to analyse a medical dataset of almost 300,000 patients, which included eye scans as well as general medical data.
Professor of Cardiovascular Physiology and Pharmacology at London’s UCL, Alun Hughes, voiced a more cautionary tone by saying that the algorithm must be tested before it could be trusted.
However, he told The Verge that it was credible due to the “long history of looking at the retina to predict cardiovascular risk”.
Google found the testing to be 70 per cent accurate about the likelihood of a patient experiencing a heart attack within five years.
This result is similar to testing methods using a patient’s blood.
The advantage of the potential of Google scans for patients is that it could flag risk with a fast, cheap and noninvasive test that could be followed up.