How Mayo Clinic researchers use AI to detect 'silent' heart disease

Applying artificial intelligence to an electrocardiogram can help identify asymptomatic left ventricular dysfunction, a precursor to heart failure, a study published in Nature Medicine found.

The researchers, from Rochester, Minn.-based Mayo Clinic, hypothesized that asymptomatic left ventricular dysfunction could be reliably detected in the EKG by a properly trained neural network.

They used Mayo Clinic data to screen 625,326 paired EKG and transthoracic echocardiograms to identify the patient population used in the analysis. The researchers created, trained, validated and tested a neural network to test their hypothesis.

The researchers found AI applied to a standard EKG reliably detects asymptomatic left ventricular dysfunction and the AI/EKG test's accuracy is comparable to other common screening tests.

Additionally, in patients without ventricular dysfunction, those who had a positive AI screen had four times the risk of developing future ventricular dysfunction, compared with those with a negative screen, the study found.

"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," said senior study author Paul Friedman, MD.

More articles on clinical leadership and infection control:
Nixing flu vaccine for hospitalized patients could be blown opportunity, study suggests
Common pain reliever worsens C. diff infections in mice
Viewpoint: FDA must take more action on antibiotic resistance 

© Copyright ASC COMMUNICATIONS 2019. Interested in LINKING to or REPRINTING this content? View our policies by clicking here.

 


IC Database-3

Top 40 Articles from the Past 6 Months