AI Identifies Heart Valve Disease from Common Imaging Test

A new artificial intelligence (AI) program trained to analyze images from a routine medical test has shown promise in detecting early signs of tricuspid heart valve disease, potentially allowing doctors to diagnose and treat patients more effectively and earlier.

The deep-learning program, developed by researchers at the Smidt Heart Institute at Cedars-Sinai (Los Angeles, CA, USA), builds on previous research that demonstrated an AI program's ability to detect heart valve disease by analyzing ultrasound images. In this new study, published in JAMA Cardiology, the team trained the AI model to identify patterns of tricuspid regurgitation in 47,312 echocardiograms collected at Cedars-Sinai between 2011 and 2021. The AI program successfully detected tricuspid regurgitation in patients, classifying the cases as mild, moderate, or severe.

The researchers then tested the program on new echocardiograms from patients who underwent the procedure at Cedars-Sinai in 2022 and from Stanford Healthcare. The AI model was able to predict the severity of tricuspid regurgitation with accuracy comparable to that of cardiologists reviewing the echocardiograms, and its results were similar to those obtained from MRI scans. Moving forward, the researchers plan to focus on gathering more detailed data about valve disease, such as the volume of blood regurgitating through the valve, and assessing outcomes if patients receive treatment for heart valve disease. The Smidt Heart Institute's team is applying AI technology across a range of cardiac imaging tests to further advance this field.

“This AI program can augment cardiologists’ evaluation of echocardiograms, images from a screening and diagnostic test that many patients with heart disease symptoms would already be getting,” said David Ouyang, MD, a research scientist in the Smidt Heart Institute and senior author of the study. “By applying AI to echocardiograms, we can help clinicians more easily detect the signs of heart valve disease so that patients get the care they need as soon as possible.”