AI-Enhanced Echocardiography Improves Early Detection of Amyloid Buildup in Heart

The disease is often missed because its symptoms and imaging features can resemble other heart conditions. Early diagnosis is crucial, however, as new drug therapies are available that can slow or stop the disease's progression. Despite the availability of these treatments, detecting cardiac amyloidosis remains challenging, as it is often misdiagnosed or undiagnosed. To improve detection, researchers have developed a highly accurate artificial intelligence (AI) model that uses echocardiography to screen for this rare and progressive type of heart failure.

The model, the first and only AI tool of its kind, that was developed by the Mayo Clinic (Rochester, MN, USA) and Ultromics, Ltd. (Oxford, UK), analyzes a single echocardiography videoclip to detect cardiac amyloidosis across all major types and distinguishes it from other similar heart conditions. It can identify the disease before formal diagnosis, offering clinicians early insights into patient condition. The team validated and tested the model on a large and multiethnic patient population and compared its abilities to other diagnostic methods for cardiac amyloidosis. The study, published in the European Heart Journal, shows that the model demonstrated an 85% sensitivity and 93% specificity, providing real-time, highly accurate detection without the need for additional invasive tests.

The AI model is currently FDA-cleared and is being used at multiple centers in the U.S. It has proven to be more effective than traditional clinical and transthoracic echo-based screening methods, providing clinicians with valuable information to guide further testing. As a result, the AI model could significantly improve the timeliness and accuracy of cardiac amyloidosis diagnosis, allowing for early intervention and treatment. The next steps involve expanding its use in clinical practice and further research to explore its full potential in heart disease management.

"This AI model is a breakthrough tool that can help us identify patients earlier so they can receive the treatment they need," said Patricia Pellikka, M.D., a cardiologist at Mayo Clinic and senior author of the study. "We found that AI performed better than traditional clinical and transthoracic echo-based screening methods, providing clinicians with stronger insights on which to base decisions for further confirmation tests."

Related Links:
Mayo Clinic
Ultromics