Study Identifies Novel Approach to Screening for Cardiac Dysfunction

Applying artificial intelligence (AI) to a standard electrocardiogram (EKG) can reliably detect and predict asymptomatic left ventricular dysfunction (ALVD), according to a new study from the Mayo Clinic.

Because there is no inexpensive, noninvasive screening tool for ALVD available, the researchers aimed to determine whether applying AI to the routine EKG could accurately identify ALVD more inexpensively and routinely.

IF YOU LIKE THIS, READ MORE...

USPSTF Updates Recommendation for ECG Screening for AF

HFpEF Is Associated With High Risk for Coronary Microvascular Dysfunction

Using paired 12-lead EKG and echocardiogram data from 44,959 patients at the Mayo Clinic, the researchers trained a convolutional neural network to identify individuals with ventricular dysfunction, defined as an ejection fraction of 35% or lower, using the EKG data alone. 

When testing an independent set of 52,870 participants, the neural network had 86.3% sensitivity, 85.7% specificity, and 85.7% accuracy.

The application of AI to an EKG was also able to predict ventricular dysfunction risk in asymptomatic individuals.

Participants without ventricular dysfunction but who had a positive AI screen were 4 times more likely to develop future ventricular dysfunction compared with those with a negative screen.

The accuracy that the AI/EKG test provides is comparable with other common screening tests such as mammography for breast cancer.

“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,” said the study’s senior author Dr Paul Friedman, chair of the Midwest Department of Cardiovascular Medicine at Mayo Clinic.

—Colleen Murphy

References:

1. Attia ZI, Kapa S, Lopez-Jimenez F, et al. Screening for cardiac contractile dysfunction using an artificial intelligence–enabled electrocardiogram. Nat Med. 2019;25:70-74. https://doi.org/10.1038/s41591-018-0240-2.

2. Mayo Clinic research uses artificial intelligence to develop inexpensive, widely available early detector of silent heart disease [press release]. Rochester, MN: Mayo Clinic; January 7, 2019. https://newsnetwork.mayoclinic.org/discussion/mayo-clinic-research-uses-artificial-intelligence-to-develop-inexpensive-widely-available-early-detector-of-silent-heart-disease. Accessed January 8, 2019