Posted in | Medical Robotics

Mayo Clinic Uses AI to Create Economical Early Detector of Silent Heart Disease

A Mayo Clinic research has discovered that applying artificial intelligence (AI) to a commonly available, inexpensive test—the electrocardiogram (EKG)—results in a simple, economical early indicator of asymptomatic left ventricular dysfunction, which is an early indicator to heart failure. The study team learned that the AI/EKG test accuracy compares positively with other typical screening tests, such as mammography for breast cancer. The findings were reported in Nature Medicine.

Image credit: Mayo Clinic

Asymptomatic left ventricular dysfunction is characterized by the existence of a weak heart pump with a danger of overt heart failure. It affects seven million Americans and is linked to reduced quality of life and longevity. But asymptomatic left ventricular dysfunction can be treated if identified.

However, an inexpensive, noninvasive, painless screening tool for asymptomatic left ventricular dysfunction is not available for diagnostic use. The Mayo research states that the best current screening test for asymptomatic left ventricular dysfunction is to measure natriuretic peptide levels (BNP), but results of BNP have been unsatisfactory. Plus the test necessitates blood tests. Left ventricular dysfunction usually is diagnosed with costly and less accessible imaging tests, such as echocardiograms, or CT or MRI scans.

Congestive heart failure afflicts more than five million people and consumes more than $30 billion in health care expenditures in the U.S. alone. 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, M.D., Senior Author and Chair of Midwest Department of Cardiovascular Medicine, Mayo Clinic

In their research, Mayo Clinic scientists hypothesized that asymptomatic left ventricular dysfunction could be dependably detected in the EKG by an appropriately trained neural network. Using Mayo Clinic stored digital data, 625,326 paired EKG and transthoracic echocardiograms were screened to identify the population to be investigated for analysis. To test their hypothesis, scientists developed, trained, validated and then tested a neural network.

The study established that AI applied to a basic EKG consistently detects asymptomatic left ventricular dysfunction. The accuracy of the AI/EKG test compares positively with other typical screening tests, such as mammography for breast cancer, prostate-specific antigen for prostate cancer, and cervical cytology for cervical cancer.

Furthermore, in patients without ventricular dysfunction, those with a positive AI screen were at four times the danger 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.

Paul Friedman, M.D., Senior Author and Chair of Midwest Department of Cardiovascular Medicine, Mayo Clinic

Co-authors of the research are: Zachi Attia; Suraj Kapa, M.D.; Francisco Lopez-Jimenez, M.D.; Paul McKie, M.D.; Dorothy Ladewig; Gaurav Satam; Patricia Pellikka, M.D.; Maurice Enriquez-Sarano, M.D.; Peter Noseworthy, M.D.; Thomas Munger, M.D.; Samuel Asirvatham, M.D.; Christopher Scott; and Rickey Carter, Ph.D., all of Mayo Clinic.

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Submit