High Street Eye Scan Can Help Predict Future Heart Attack Risk

Dr Rob Hicks

January 26, 2022

Retinal imaging is common place in high street opticians these days, being used to help identify not only eye disease but also systemic disease such as hypertension and diabetes.

Now research lead by the University of Leeds, published in the journal Nature Machine Intelligence, has established that an artificial intelligence (AI) system can, by reading conventional retinal scans for signs of heart disease, predict with 70% to 80% accuracy if a person is at risk of a heart attack over the next year.

For their research scientists developed an AI system that analyses the retinal eye scans performed routinely at an optician practice or in an eye clinic. To train the system they used deep learning techniques -  a complex series of algorithms that enable computers to identify patterns in data and to make predictions – and uses data from the UK Biobank.

The authors of the study explained how “recent studies have shown that biomarkers on retinal images, for example, retinal blood vessel density or tortuosity, are associated with cardiac function and may identify patients at risk of coronary artery disease".

AI Unravels Nature’s Complex Patterns

Retinal scans and cardiac scans from more than 5000 people were analysed by the AI system during the deep learning process. The AI system identified associations between pathology in the retina and changes in the patient’s heart. Once the image patterns were learned, the AI system could estimate the size and pumping efficiency of the left ventricle from retinal scans alone.

Sven Plein, British Heart Foundation Professor of Cardiovascular Imaging at the University of Leeds and one of the authors of the research paper, said: “The AI system is an excellent tool for unravelling the complex patterns that exist in nature, and that is what we have found here – the intricate pattern of changes in the retina linked to changes in the heart.” 

Revolutionises Screening of Cardiac 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.  

Professor Alex Frangi, who holds the Diamond Jubilee Chair in Computational Medicine at the University of Leeds and is a Turing Fellow at the Alan Turing Institute, supervised the research. He said: “This technique opens-up the possibility of revolutionising the screening of cardiac disease,” adding that “the scans could also be used to track the early signs of heart disease”.

Time and Cost Saving Potential

Assessment of size and pumping efficiency of the left ventricle currently requires echocardiography or magnetic resonance imaging of the heart. Not only can these investigations be expensive they are often only available in a hospital setting, adding to healthcare costs, and to waiting times and inconvenience for patients.

Professor Frangi highlighted how, “Retinal scans are comparatively cheap and routinely used in many optician practices. As a result of automated screening, patients who are at high risk of becoming ill could be referred to specialist cardiac services.”

Chris Gale, Professor of Cardiovascular Medicine at the University of Leeds and a Consultant Cardiologist at Leeds Teaching Hospitals NHS Trust, and one of the authors of the research paper, said: “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.” 

The authors concluded by saying: “Our results indicate that one could identify patients at high risk of future myocardial infarction from retinal imaging available in every optician and eye clinic.”

The study involved a worldwide collaboration of scientists, engineers and clinicians from the University of Leeds; Leeds Teaching Hospitals’ NHS Trust; the University of York; the Cixi Institute of Biomedical Imaging in Ningbo, part of the Chinese Academy of Sciences; the University of Cote d’Azur, France; the National Centre for Biotechnology Information and the National Eye Institute, both part of the National Institutes for Health in the US; and KU Leuven in Belgium. 

Diaz-Pinto, A., Ravikumar, N., Attar, R. et al. Predicting myocardial infarction through retinal scans and minimal personal information. Nat Mach Intell (2022). DOI: 10.1038/s42256-021-00427-7


Comments on Medscape are moderated and should be professional in tone and on topic. You must declare any conflicts of interest related to your comments and responses. Please see our Commenting Guide for further information. We reserve the right to remove posts at our sole discretion.