AI Accurately Detects Deadly Heart Condition

New tool offers hope for earlier diagnosis and treatment of cardiac amyloidosis.

A novel artificial intelligence (AI) model shows promise in screening for cardiac amyloidosis, a progressive heart disease. Early detection is crucial, as new treatments can significantly improve patient outcomes, according to a recent study in the European Heart Journal.

Key Development

Researchers from the Mayo Clinic and Ultromics, Ltd., developed the AI, training it to recognize cardiac amyloidosis in echocardiograms. A cardiologist at the University of Chicago Medicine, co-lead author Jeremy Slivnick, MD, noted that the AI analyzes echocardiogram videos to detect cardiac amyloidosis, distinguishing it from other similar conditions.

High Accuracy Demonstrated

The AI tool demonstrated an 85% accuracy rate in identifying patients with cardiac amyloidosis and a 93% accuracy rate in correctly ruling it out. Moreover, the tool’s effectiveness remained consistent across various types of cardiac amyloidosis and diverse patient populations.

Outperforming Traditional Methods

The study found the AI model outperformed existing clinical scoring methods, enabling doctors to more easily identify individuals who require advanced imaging or further evaluation. According to the American Heart Association, early diagnosis and treatment can significantly improve the quality of life and survival rates for patients with cardiac amyloidosis (American Heart Association).

“It was exciting to confirm that artificial intelligence can give clinicians reliable information to augment their expert decision-making process,”

—Jeremy Slivnick, Cardiologist at the University of Chicago Medicine

Cardiac Amyloidosis Explained

Cardiac amyloidosis occurs when abnormal proteins accumulate in the heart muscle, causing stiffness and impairing its ability to pump blood effectively. Timely diagnosis is essential to take advantage of available life-prolonging drug treatments.

“Unfortunately, cardiac amyloidosis can be challenging to diagnose, because it’s often difficult to distinguish from other heart issues without a burdensome amount of testing,”

—Jeremy Slivnick, Cardiologist at the University of Chicago Medicine

Implementation and Future Impact

The AI model has already received FDA clearance and is being implemented in hospitals nationwide. Researchers hope its widespread use in routine cardiac care will become standard practice.

Slivnick stated:

“This AI model provides a practical solution. Because it automatically analyzes a common echocardiogram view, it can easily integrate into everyday clinical practice without causing hassle or sacrificing diagnostic accuracy.”

—Jeremy Slivnick, Cardiologist at the University of Chicago Medicine