Mayo Clinic AI enables EKGs to screen for hypertrophic cardiomyopathy

Andrea Park - Print  | 

An artificial intelligence approach developed by Mayo Clinic researchers and physicians could enable earlier detection of hypertrophic cardiomyopathy, an often-asymptomatic heart condition that is among the leading causes of sudden death in young athletes.

The technique is described in a new study published by the team from the Rochester, Minn.-based health system in the Journal of the American College of Radiology. On its own, current electrocardiogram technology is limited in its ability to detect the condition, which causes a thickening of the walls of the heart, but applying the new AI technique to standard 12-lead EKGs was found to be a remarkably accurate predictor of hypertrophic cardiomyopathy.

In a Mayo Clinic news release, the authors described the convolutional neural network AI's accuracy in detecting the condition in patients with both normal and abnormal EKGs, with the latter group including patients with left ventricular hypertrophy, aortic stenosis and other related heart conditions.

They also found the technique performed especially well in patients under 40 years old, which is among the study's more significant findings, according to Konstantinos Siontis, MD, a resident cardiologist at Mayo Clinic and co-first author of the study. That finding "highlights [the AI's] potential value in screening younger adults," he said.

The researchers plan to continue to test the technique on other subgroups of patients to further refine its findings. "We also need to learn more about what specific characteristics of hypertrophic cardiomyopathy this network is detecting. We hope to learn how to apply this technology to screening and managing patients in families affected by this disease," said Peter Noseworthy, MD, a Mayo Clinic cardiologist.

More articles on AI:
Sutter Health deploys AI platform to catch imaging discrepancies
AI measures blood flow in real time, predicting heart attack and stroke, study finds
6 best practices to help health systems get the most out of AI

© Copyright ASC COMMUNICATIONS 2020. Interested in LINKING to or REPRINTING this content? View our policies by clicking here.

To receive the latest hospital and health system business and legal news and analysis from Becker's Hospital Review, sign-up for the free Becker's Hospital Review E-weekly by clicking here.