AI May Help Detect Irregular Heartbeat In The ECG Test
Editorials News | Aug-07-2019
New York: Artificial Intelligence (AI) can detect the signs of an irregular heart rhythm: atrial fibrillation (AF) on an electrocardiogram (ECG), even if the heart is in normal rhythm at the time of a test, according to new research of Mayo Clinic.
AI-enabled EKG can detect recent atrial fibrillation that occurred without symptoms or is imminent, potentially improving treatment options.
The research could improve the efficiency of EKG, a non-invasive and widely available method of detecting heart disease, said the study published in The Lancet.
While it is common, atrial fibrillation is often fleeting and difficult to diagnose.
"When people arrive with a stroke, we really want to know if they had atrial fibrillation in the days before the stroke, because it guides treatment," said Paul Friedman, president of the Department of Cardiovascular Medicine at Mayo Clinic.
Anticoagulants are very effective in preventing another stroke in people with atrial fibrillation.
"For those without atrial fibrillation, the use of anticoagulants increases the risk of bleeding without substantial benefit. That is important knowledge. We want to know if a patient has AF," Friedman said.
The researchers tested AI on normal rhythm electrocardiograms from a group of 36,280 patients, of which 3,051 had atrial fibrillation. The AI-enabled EKG correctly identified the subtle patterns of atrial fibrillation with an accuracy of 90 percent.
If proven, AI-guided ECGs could direct adequate treatment for disease caused by atrial fibrillation, even without symptoms.
In addition, this technology can be processed using a smartphone or watch, which makes it easily available on a large scale.
By: Preeti Narula