AI system can predict risk of heart attack based on retinal scan
An international team of researchers have developed an AI system that can identify patients who are likely to have a heart attack over the next year. The system reads retinal scans that are already commonly used in eye clinics.
Doctors have recognised that changes to the tiny blood vessels in the retina are indicators of broader vascular disease, including problems with the heart. An international team of researchers have now developed an AI system that analyses retinal scans to identify patients at a high risk of a heart attack.
The system has a 70% to 80% accuracy. It could help as an additional referral mechanism for in-depth cardiovascular investigation. As a result, preventative treatments could be started sooner.
The study was led by Alex Frangi, who is a visiting professor at KU Leuven (Processing Speech and Images / Department of Cardiovascular Sciences) and is also affiliated with the University of Leeds and the Alan Turing Institute. Professor Frangi: "Cardiovascular diseases, including heart attacks, are the leading cause of early death worldwide. Our technique opens up the possibility of revolutionising the screening of cardiac disease. Retinal scans are comparatively cheap and routinely used in many eye clinics. As a result of automated screening, patients who are at high risk of becoming ill could be referred to specialist cardiac services more quickly. The scans could also be used to track early signs of heart disease."
The researchers used deep learning, a complex series of algorithms that enable computers to identify patterns in data and to make predictions.
During the deep learning process, the AI system analysed the retinal and cardiac scans of more than 5,000 people. The system identified associations between pathology in the retina and changes in the patient’s heart. The UK Biobank provided data for the study.
Once the image patterns were learned, the AI system could estimate the size and pumping efficiency of the left ventricle, one of the heart’s four chambers, from retinal scans alone. An enlarged ventricle is linked with an increased risk of heart disease.
With information on the estimated size of the left ventricle and its pumping efficiency combined with basic demographic data about the patient, their age and sex, the AI system could make a prediction about their risk of a heart attack over the subsequent 12 months.
Currently, details about the size and pumping efficiency of a patient’s left ventricle can only be determined if they have diagnostic tests such as echocardiography or MRI scan of the heart. increasing healthcare costs and waiting times in other countries.