Skip to NavigationSkip to content

Google develops AI to predict cardiovascular risk

Published on 21/02/18 at 09:15am

Google and Verily Life Sciences, a subsidiary within Alphabet, focused on developing health-tech, have revealed the fruits of a combined effort to harness AI to provide tools to healthcare professionals.

In this particular case, Google announced that AI technology it had developed was able to predict, with 70% accuracy, the risk of a cardiovascular event for patients over a five-year period, only 2% inferior to tests currently in use.

The AI works not by analysing blood samples but instead by examining images of the retinas of patients.

The technology can determine, through assessing the blood vessels at the back of the eye, a whole range of information: whether the subject was a smoker, probable age, gender and blood pressure.

Using this picture of the health of the individual meant that the AI was able to predict, with a good degree of accuracy, how likely someone was to have a cardiovascular event, but could also arrive with the advantage of being a far more efficient screening process compared with taking blood samples to examine levels of cholesterol.

The scientists from Google and Verily used a dataset of close to 300,000 patients in order for the AI to build up an understanding of risk factors seen in retinal scans.

Use of the eye as a barometer for heart health is not as unusual as it sounds; the blood vessels have been commonly understood as a good indicator for blood pressure and other factors that are related to cardiovascular risk.

A blog post by Michael McConnell, Head of Cardiovascular Health Innovations at Verily, reads: “Machine learning allows researchers to surface signals in data-rich environments, like images, that were previously difficult to examine given their complexity and enables broader, deeper scientific discovery. The opportunity to one day readily understand the health of a patient’s blood vessels, key to cardiovascular health, with a simple retinal image could lower the barrier to engage in critical conversations on preventive measures to protect against a cardiovascular event. This is promising, but early research – more work must be done to develop and validate these findings on larger patient cohorts before this can arrive in a clinical setting.”

Though it may be early days for the technology, with a success rate not far from conventional tests, if its accuracy can be further refined and an efficient means of rolling it out explored, it might not be too long before AI is leaned upon to provide assistance in a clinical setting.

Ben Hargreaves

Mission Statement
Pharmafile.com is a leading portal for the pharmaceutical industry, providing industry professionals with pharma news, pharma events, pharma service company listings and pharma jobs,
Site content is produced by our editorial team exclusively for Pharmafile.com and our industry newspaper Pharmafocus. Service company profiles and listings are taken from our pharmaceutical industry directory, Pharmafile, and presented in a unique Find and Compare format to ensure the most relevant matches