(ORDO NEWS) — Early, accurate and simple diagnosis is important in almost any disease that can be named, including cardiovascular disease. New research shows that direct eye scanning can identify patients at increased risk of cardiovascular disease later in life.
If such a diagnostic method can be developed, it will be very important – scanning is fast, non-invasive and reliable, and the sooner it is possible to identify the risk of cardiovascular diseases, the more doctors and their patients can do to prevent them.
Key to the new approach is a deep learning algorithm, a type of artificial intelligence (AI)-based neural network that can be trained on large datasets to identify patterns.In this case, the researchers trained him to look for tiny blood vessel changes in the retina, a link that has been widely discussed in the medical literature.
In a new paper describing the results, the team reports that their tool was able to predict the risk of future myocardial infarctions with an accuracy of about 70 percent.
“The AI system is able to identify people undergoing routine eye exams who are at increased risk for cardiovascular disease in the future, allowing early preventive treatment to prevent premature cardiovascular disease,” says Chris Gale, professor of cardiovascular medicine. from the University of Leeds in the UK.
To create the tool, retinal scans and ECGs of 5,663 people from the UK Biobank database were analyzed by a computer program, with the system programmed to associate changes in one scan with changes in another.
After going through a learning process and studying emerging patterns, the AI was smart enough to correlate heart health with blood vessels in the retina: in particular, the size and efficiency of the left ventricle of the heart, which has already been associated with an increased likelihood of heart disease.
This score was combined with age, gender, and basic demographic information to provide an overall risk score. This could be used as a secondary referral method, the researchers say.
“The AI system is a great tool for unraveling the complex patterns that exist in nature, and that’s what we found – a complex pattern of changes in the retina associated with changes in the heart,” says Sven Plein, professor of cardiovascular imaging at the University of Leeds. .
Currently, assessing the condition of the left ventricle – one of the four chambers of the heart – requires expensive tests that must be performed in a hospital. For many people around the world, this means problems with access and affordability.
However, retinal scans are already regularly performed in optical clinics, so AI analysis for heart disease risk can be added to it. Those who are at high risk of developing cardiovascular disease can be referred to specialists.
Given that millions of people die every year from cardiovascular disease around the world – in the US alone, the figure is one person every 36 seconds – a system like this one has the potential to make a significant difference, although this will require more research and data.
“Cardiovascular disease, including heart attacks, is the leading cause of early death worldwide and the second leading cause of death in the UK,” says Alex Frangi, chair of computational medicine at the University of Leeds.”This leads to chronic ill health and suffering throughout the world.”
—
Online:
Contact us: [email protected]
Our Standards, Terms of Use: Standard Terms And Conditions.