Now, scientists can find out about patients’ heart issues in a completely new way – while analyzing eye scans. Even the simplest visit to an eye clinic will help doctors identify if their patient is at risk of a heart attack.
Identifying Heart Issues
Eyes can truly say more than words. In 2022, scientists found out that changes in the retina can predict heart issues. Turns out, when blood vessels of the eyes change they can indicate other vascular diseases. The University of Leeds led the research that included the use of an AI system. The team trained it to read incoming retinal scans and identify people prone to having a heart attack in the following year. Called “Predicting Infarction Through Your Retinal Scans and Minimal Personal Information,” the paper from the research also used deep learning – a list of algorithms that teach computers to predict. In the end, the trained AI system had an accuracy of between 70% and 80%. While not the first choice for the doctors, this method can be a second step to recognizing heart disease.
Professor Alex Frangi supervised the research and deep learning process. He holds the Diamond Jubilee Chair in Computational Medicine in the School of Computing at the University of Leeds and is a Turing Fellow at the Alan Turing Institute. “Cardiovascular diseases, including heart attacks, are the leading cause of early death worldwide and the second-largest killer in the UK. This causes chronic ill-health and misery worldwide,” he commented. “This technique opens up the possibility of revolutionizing the screening of cardiac disease.” He added that it would be more affordable as well because retinal scans are cheap.
Combining Eye Scans With Cardiac Scans
The University of Leeds team received their study data from the UK Biobank. “The AI system has the potential to identify individuals attending routine eye screening who are at higher future risk of cardiovascular disease, whereby preventative treatments could be started earlier to prevent premature cardiovascular disease,” said Chris Gale, one of the research authors. He’s also a Professor of Cardiovascular Medicine at the University of Leeds and a Consultant Cardiologist at Leeds Teaching Hospitals NHS Trust. In the research, the AI system looked through 5,000 retinal scans and cardiac scans. Then, the system found parallels between pathology in the retina and changes in the heart. Based on the pictures, the AI learned the organ patterns, thus further identifying the size and pumping efficiency of the left ventricle.
After the learning and identifying process, the AI system recognized the essential information about the patients, including their age and sex. At that stage, it could predict how close they are to a heart attack in the next 12 months. Unfortunately, this technology can only be used on patients who went through echocardiography or magnetic resonance imaging of the heart – they are not as affordable and unreachable outside serious hospitals.
“The AI system is an excellent tool for unravelling the complex patterns that exist in nature, and that is what we have found,” commented Sven Plein, British Heart Foundation Professor of Cardiovascular Imaging at the University of Leeds and one of the authors of the research paper. “The intricate pattern of changes in the retina linked to changes in the heart.”