AI-enabled EKG proves powerful screening tool for heart disease

Researchers at the Mayo Clinic have applied artificial intelligence to a routine method of measuring the heart’s electrical activity to identify patients with asymptomatic left ventricular dysfunction.

According to Mayo officials, until now there hasn’t been an inexpensive, noninvasive, painless screening tool for asymptomatic left ventricular dysfunction—a precursor to heart failure—available for diagnostic use.

However, they contend that an AI-enabled electrocardiogram (EKG) has proven to be a “powerful screening tool” for individuals with ALVD, demonstrating accuracy on par with other common tests, such as prostate-specific antigen for prostate cancer, mammography for breast cancer and cervical cytology for cervical cancer.

Gonda_building_Mayo.jpg

Researchers trained a convolutional neural network to identify patients with asymptomatic left ventricular dysfunction using paired 12-lead EKG and echocardiogram data. What they found was that AI applied to a standard EKG reliably detects ALVD.

Results of their study were published on Monday in the journal Nature Medicine.

Also See: Mayo, Eko team on machine learning to detect heart abnormalities

“Congestive heart failure afflicts more than 5 million people and consumes more than $30 billion in healthcare expenditures in the U.S. alone,” says Paul Friedman, MD, senior author and chair of the Midwest Department of Cardiovascular Medicine at Mayo Clinic. “The ability to acquire an ubiquitous, easily accessible, inexpensive recording in 10 seconds—the EKG—and to digitally process it with AI to extract new information about previously hidden heart disease holds great promise for saving lives and improving health.”

Friedman also notes that for patients in the study without ventricular dysfunction, those with a positive AI screen were at four times the risk of developing future ventricular dysfunction, compared with those with a negative screen.

“In other words, the test not only identified asymptomatic disease, but also predicted risk of future disease, presumably by identifying very early, subtle EKG changes that occur before heart muscle weakness,” he adds.

For reprint and licensing requests for this article, click here.