ECG using AI can help early detection of heart condition

New York:  Applying Artificial Intelligence (AI) to a widely available, inexpensive test can help detect a heart condition that is a precursor to heart failure, according to a new study.

Using AI with the electrocardiogram (ECG) results in a simple, affordable early indicator of asymptomatic left ventricular dysfunction which is typically diagnosed with expensive and less accessible imaging tests, such as echocardiograms, CT or MRI scans, researchers from Minnesota's Mayo Clinic said.

Asymptomatic left ventricular dysfunction is characterised by the presence of a weak heart pump with a risk of overt heart failure which is associated with reduced quality of life and longevity. 

The study found that AI applied to a standard ECG reliably detects asymptomatic left ventricular dysfunction. 

"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," the Mayo Clinic's Paul Friedman said. 

For the study, using digital data of 625,326 persons, the team paired ECG and transthoracic echocardiograms. 

The accuracy of the AI/ECG test compares favourably with other common screening tests, such as prostate-specific antigen for prostate cancer, mammography for breast cancer and cervical cytology for cervical cancer, according to the research published in the journal Nature Medicine. 

In addition, patients without ventricular dysfunction, but with a positive AI screen were at four times the risk of developing future ventricular dysfunction, compared with those with a negative screen, the results showed. 

"The test not only identified asymptomatic disease but also predicted risk of future disease, presumably by identifying very early, subtle ECG changes that occur before heart muscle weakness," Friedman said.

Asymptomatic left ventricular dysfunction is treatable when identified, the study noted.