Artificial intelligence: retinal scan reveals heart attack risk

According to head of research Alex Franghi and his team, the prediction accuracy is 70 to 80 percent. "This technology opens up the possibility of revolutionizing the screening of heart disease," says Franghi. Retinal scans are comparatively inexpensive and are routinely carried out in many opticians' practices. As a result of the automated screening, patients who are at high risk of becoming ill would then be referred to cardiologists who could possibly still avert a heart attack.

During the learning process, the AI system analyzed the retina and heart scans of over 5,000 people. It identified parallels between changes in the patient's retina and heart. Once the system had learned its lesson, it was able to estimate the size and pumping efficiency of the left ventricle, one of the four chambers of the heart, from retinal scans alone.

An enlarged ventricle is associated with an increased risk of heart disease. Using information about the estimated size of the left ventricle and its pumping efficiency in combination with basic demographic data about the patient, their age and gender, the AI system can make a prediction about the risk of a heart attack in the following twelve months.

Alternatives are often expensive

Currently, details about the size and pumping efficiency of a patient's left ventricle can only be determined by echocardiography or magnetic resonance imaging. These diagnostic tests are expensive, making them unsuitable for pre-invasive screening. In addition, the necessary technology is often only available in hospitals that are difficult to reach for people in countries with less well-equipped healthcare systems. According to the experts, the new AI system is an excellent tool for unraveling the complex patterns of the retina and making them usable for infarct prognoses.

Source: Presstetext.com