News

New artificial intelligence algorithim detects overlooked heart diseases

Published

on

Scientists at Cedar-Sinai have created an artificial intelligence (AI) tool that can effectively identify and distinguish between two life-threatening heart conditions.

The two-step novel algorithm was tested on over 34,000 cardiac ultrasound videos from Cedar-Sinai and Stanford Healthcare’s echocardiography laboratories. It can distinguish between two heart conditions that are often missed including hypertrophic cardiomyopathy and cardiac amyloidosis.

When the tool was applied to the clinical images, it identified specific features related to the thickness of walls and the size of heart chambers. This efficiently flags certain patients as having the potential for unrecognised cardiac diseases.

Without comprehensive testing, cardiologists can find it difficult to distinguish between diseases that are similar, changes in heart shape or size which can often be attributed to ageing. This algorithm not only distinguishes abnormal from normal but also detects any underlying warning signals for diseases before it can get to a point that it impacts a person’s health. Earlier diagnosis can mean starting effective treatments sooner, preventing adverse clinical events and improving the quality of life.

Researchers are planning to launch clinical trials for patients that have been flagged by the AI algorithm for suspected cardiac problems. The patients that are enrolled will be seen by experts in the cardiac amyloidosis program at Smidt Heart Institute.

David Ouyang, MD, a cardiologist in the Smidt Heart Institute and senior author of the study said: “These two heart conditions are challenging for even expert cardiologists to accurately identify, and so patients often go on for years to decades before receiving a correct diagnosis. Our AI algorithm can pinpoint disease patterns that can’t be seen by the naked eye, and then use these patterns to predict the right diagnosis.”

“The algorithm identified high-risk patients with more accuracy than the well-trained eye of a clinical expert. This is because the algorithm picks up subtle cues on ultrasound videos that distinguish between heart conditions that can often look very similar to more benign conditions, as well as to each other, on initial review.” Ouyang stated.

Comprehensive testing

Cardiac amyloidosis is often referred to as ‘stiff heart syndrome’ and it is a disorder caused by deposits of an abnormal protein the heart tissue. As the amyloid builds up, it can take the place of the healthy heart muscle which makes it difficult for the heart to work properly. It often goes undetected because a patient may not have any symptoms or occasional symptoms.

The disease is more common in older, Black men or patients with cancer or diseases involving inflammation. The researchers highlighted that AI may be an important tool for improving healthcare equity.

Hypertrophic cardiomyopathy is a disease that causes the heart muscle to thicken and stiffen. It means the heart is less able to relax and fill with blood. This results in damage to heart values, fluid build-up in the lungs and abnormal heart rhythms.

Both heart conditions often appear very similar on echocardiograms which is the most commonly used cardiac imaging diagnostic. In the early stages, they can mimic the appearance of a healthy heart that has changed naturally due to ageing.

Ouyang said: “One of the most important aspects of this AI technology is not only the ability to distinguish abnormal from normal but also to distinguish between these abnormal conditions because the treatment and management of each cardiac disease are very different.”

6 Comments

Trending stories

Exit mobile version