Mayo Clinic researchers use AI, EKG test to detect heart condition

AI applied to an electrocardiogram (EKG) test reliably detected asymptomatic left ventricular dysfunction (ALVD)—a precursor to heart failure—and predicted which patients were most at risk of developing the condition in the future, according to a Mayo Clinic study published in Nature Medicine.

The testing accuracy is comparable to other common screening tests, such as mammography for breast cancer, and offers a cheaper, easier solution than current methods.

"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," Paul Friedman, MD, senior study author and chair of the Midwest Department of Cardiovascular Medicine at Mayo Clinic, said in a prepared statement.

For the study, researchers created their own convolutional neural network and used 12-lead EKG and echocardiogram data from nearly 45,000 Mayo Clinic patients to train the network to identify patients with ventricular dysfunction. The network was then tested on an independent dataset of more than 52,000 patients, and the results revealed that AI applied to a standard EKG can reliably detect ALVD.

According to researchers, ALVD is described by the presence of a weak heart pump with a risk of overt heart failure. Currently, about 7 million Americans are affected by the condition and, though its treatable when identified, there is no inexpensive, noninvasive screen tool for condition.

The network model achieved an area under the curve (AUC) of 0.93, a sensitivity of 86.3 percent, a specificity of 65.7 percent and an accuracy of 85.7 percent. Additionally, in patients without the condition, the network predicted that those with a positive AI screen were four times more likely 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,” Friedman said.

""

Danielle covers Clinical Innovation & Technology as a senior news writer for TriMed Media. Previously, she worked as a news reporter in northeast Missouri and earned a journalism degree from the University of Illinois at Urbana-Champaign. She's also a huge fan of the Chicago Cubs, Bears and Bulls. 

Trimed Popup
Trimed Popup