Photographs of your retina can be used to predict your risk factors for cardiovascular disease with a new system created by Artificial Intelligence (AI) researchers at Google and Verily Life Sciences.
According to the American Heart Association, heart disease is the leading cause of death in the world, accounting for more than 17.3 million deaths per year in 2013, a number that is expected to grow to more than 23.6 million by 2030.
Can You Predict a Heart Attack?
The idea that an eye scan could provide an early warning of risks, hopefully in time to change behavior, is both revolutionary and exciting.
A recent study published in the Nature Biomedical Engineering journal demonstrated that an AI algorithm created by Google AI and Verily can predict whether a person is likely to suffer a major cardiovascular event within the next five years, based solely on photos of their retinas. According to the study, their predictions work as well as present methods with one primary benefit being that their methods are less invasive.
Doctors often spot medical conditions including diabetes, extreme high blood pressure, high cholesterol, and some cancers during eye exams. So this new research isn’t a big surprise to many.
In their study, Verily and Google researchers utilized AI software to identify cardiovascular risks by analyzing retina photos and health data from 284,335 patients.
Common risk factors for heart disease include age, family history, hypertension, high cholesterol, obesity and if the person is a smoker. Based on an eye scan, their algorithm was able to predict a person’s age to within 3.26 years, smoking status with 71% accuracy, and blood pressure within 11 units of the upper number reported in their measurement. Because the algorithm was so effective at assessing these factors, the AI researchers decided to see how well it could predict major cardiovascular events. Using data from 150 patients that had suffered major cardiovascular events within five years of their eye scan, the algorithm predicted the correct scan 70% of the time correlating to the cardiovascular events.
The system creates heat-maps of specific areas it focuses on. In this case, the researchers paid particular attention to blood vessels to calculate blood pressure.
Overall, this new study is transforming the way scientists study the human body and may aid in giving researchers and doctors a more complete analysis of a person’s overall health.
However, as promising as these results are, they are preliminary. According to Dr. Michael McConnell, the Head of Cardiovascular Health Innovations at Verily. “More work must be done to develop and validate these findings on larger patient cohorts before this can arrive in a clinical setting.”