AI can predict a heart attack – from a routine eye test
LEEDS, UK (StudyFinds.org) — An artificial intelligence system is able to detect if someone will have a heart attack in the coming year — through routine eye scanning.
A team from the University of Leeds believe this AI tool opens the door to a simple and cheap screening program for the world’s number one killer. Their tests reveal that the computer can predict patients at risk for a heart attack over the next 12 months with up to 80% accuracy. This breakthrough adds to the proof that our eyes are not just “windows to the soul”, but windows to overall healthalso.
“Cardiovascular disease, including heart attack, is the leading cause of premature death worldwide and the second leading cause of death in the UK. This causes chronic health problems and misery all over the world,” says project supervisor Professor Alex Frangi in a university outing.
“This technique opens up the possibility of revolutionizing heart disease screening. Retinal scanners are relatively inexpensive and commonly used in many opticians’ offices. With automated screening, patients at high risk of getting sick could be referred to specialized cardiac services,” adds Frangi.
“The system could also be used to track signs of heart disease.”
Look at the retina to discover red flags in the heart
The retina is a small membrane at the back of the eye containing light-sensitive cells. Doctors have found that changes to tiny blood vessels can reference to vascular diseaseincluding heart problems.
The study authors used an advanced type of AI, known as deep learning, to teach the machine to automatically read more than 5,000 eye scans. The scans come from routine eye tests during visits to opticians or eye clinics. All participants are part of the UK Biobank, which tracks the health of half a million adults.
Deep learning is a complex series of algorithms that allow machines to make predictions based on patterns of data. The technique, described in the review Intelligence of natural machinescould revolutionize cardiac therapy, researchers say.
“The AI system has the potential to identify individuals who participate in routine eye screening who are at higher future risk of cardiovascular disease, whereby preventative treatments could be started earlier to prevent premature cardiovascular disease” , says co-author Professor Chris Gale, consultant cardiologist at Leeds Teaching Hospitals NHS Trust.
The study identified associations between retinal pathology and changes in the patient’s heart. Once the system learned each image pattern, the AI was able to estimate the size and pumping efficiency of the left ventricle from the retinal scans alone.
It is one of the four chambers of the heart. An enlarged ventricle can increase the risk of heart disease. The computer combined the estimated size of the left ventricle and its pumping efficiency with data such as age and gender.
The eyes say a lot about sickness and death
Currently, doctors determine this information using an MRI (magnetic resonance imaging) or echocardiography of the heart. Diagnostic tests are expensive and are often only available at a hospital. Testing may be inaccessible for many people in countries with less modern health systems. They also increase health care costs and waiting times in rich countries.
“The AI system is a great tool for unraveling the complex patterns that exist in nature, and that’s what we found – the complex pattern of changes in the retina linked to changes in the heart,” adds the co. -author Sven Plein of the British Heart Foundation.
A recent study found a similar link between the biology retinal aging and mortality. Those whose retinas were “older” than their actual age were up to 67% more likely to die within the next decade.
South West News Service writer Mark Waghorn contributed to this report.