Eye can be used as a window into cardiac/Heart problems.

Scientists have created an artificial intelligence (AI) system that can analyze eye scans taken during a regular visit to an optician or eye clinic and identify people who are at high risk of having a heart attack.

Changes in the microscopic blood vessels in the retina have been recognized by doctors as markers of larger vascular disease, including heart difficulties.

Deep learning techniques were used to teach the AI system to automatically interpret retinal scans and identify those patients who were likely to have a heart attack during the next year, according to the study lead by the University of Leeds.

Deep learning is a set of techniques that allows computers to recognize patterns in data and anticipate outcomes.

The researchers claim in the journal Nature Machine Intelligence that the AI system had an accuracy of 70% to 80% and might be utilized as a second referral mechanism for in-depth cardiovascular evaluation.

The application of deep learning to the interpretation of retinal scans has the potential to change the way patients are checked for indicators of heart disease on a regular basis.

Professor Alex Frangi, who is a Turing Fellow at the Alan Turing Institute and holds the Diamond Jubilee Chair in Computational Medicine at the University of Leeds, oversaw the research. "Cardiovascular disorders, including heart attacks, are the leading cause of premature mortality worldwide and the second-highest cause of death in the United Kingdom," he stated. This results in long-term illness and unhappiness all across the planet.

"This approach has the potential to revolutionize the detection of heart illness." Retinal scans are relatively inexpensive and are routinely performed in many optometrist offices. Patients at high risk of becoming ill could be directed to expert cardiac care as a result of automated screening. The scans could also be utilised to monitor heart disease symptoms early on."

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 Center for Biotechnology Information and the National Eye Institute, both part of the National Institutes of Health in the United States, and KU Leuven in Belgium collaborated on the research.

The study used data from the UK Biobank.

One of the research paper's authors was Chris Gale, a Professor of Cardiovascular Medicine at the University of Leeds and a Consultant Cardiologist at Leeds Teaching Hospitals NHS Trust.

"The AI system has the potential to detect individuals who are at higher future risk of cardiovascular disease during routine eye screening, allowing preventative medications to be started sooner to prevent premature cardiovascular disease," he said.

Learning at a deeper level

The AI system analysed the retinal scans and cardiac scans of over 5,000 patients during the deep learning phase. The AI system discovered links between retinal pathology and changes in the patient's heart.

After learning the visual patterns, the AI system could use retinal scans alone to estimate the size and pumping efficiency of the left ventricle, one of the heart's four chambers. An higher risk of heart disease has been related to a larger ventricle.

The AI system could create a forecast about the patient's risk of a heart attack over the next 12 months using information on the estimated size of the left ventricle and its pumping efficiency, as well as basic demographic data such as their age and sex.

Currently, only diagnostic techniques such as echocardiography or magnetic resonance imaging of the heart can identify the size and pumping efficiency of a patient's left ventricle. These diagnostic procedures can be costly and are typically only available in a hospital setting, rendering them inaccessible to people in countries with under-resourced healthcare systems — or driving up healthcare expenditures and waiting times in rich countries unnecessarily.

"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," said Sven Plein, British Heart Foundation Professor of Cardiovascular Imaging at the University of Leeds and one of the research paper's authors.