Mayo Clinic trial signals potential for AI-guided heart disease detection

An artificial intelligence-enabled electrocardiogram helped identify patients with low ejection fraction who previously "would have slipped through the cracks."
By Kat Jercich
12:22 PM

Photo by FG Trade/Getty Images

The Mayo Clinic released results of a trial this week that suggests potential for artificial intelligence to assist with early diagnosis of some types of heart disease.  

The study, published in Nature Medicine on Thursday, found that an AI-enabled electrocardiogram increased the diagnosis of low ejection fraction.  

"The AI-enabled EKG facilitated the diagnosis of patients with low ejection fraction in a real-world setting by identifying people who previously would have slipped through the cracks," said Dr. Peter Noseworthy, a Mayo Clinic cardiac electrophysiologist who was the senior author on the study, in a press release.    

WHY IT MATTERS

Ejection fraction is a measurement of how much blood the left ventricle pumps out with each contraction. A lower-than-normal ejection fraction can be a sign of heart failure.  

Diagnosing low ejection fraction early can be key to effective treatment. And as the Mayo Clinic notes, an echocardiogram can do so, but it is time-consuming and resource-heavy. By contrast, an EKG is readily available, inexpensive and fast.  

The ECG AI-Guided Screening for Low Ejection Fraction, or EAGLE, was aimed at determining whether an AI-enabled EKG algorithm trial could help improve the diagnosis of this condition.  

Over eight months, 22,641 adult patients received an EKG under the medical supervision of 348 primary care clinicians throughout Minnesota.   

Clinicians in the intervention group were "alerted to a positive screening result for low ejection fraction via the electronic health record, prompting them to order an echocardiogram to confirm," read the press release.  

The AI found positive results in 6% of the patients. Although the proportion who received an echocardiogram was similar overall, the AI intervention increased the diagnosis of low ejection fraction.  

"To put it in absolute terms, for every 1,000 patients screened, the AI screening yielded five new diagnoses of low ejection fraction over usual care," said Xiaoxi Yao, a health outcomes researcher in cardiovascular diseases at Mayo Clinic and first author on the study, in a statement.  

The low ejection fraction algorithm has received Food and Drug Administration breakthrough designation.  

"With EAGLE, the information was readily available in the electronic health record, and care teams could see the results and decide how to use that information," said Noseworthy.  

THE LARGER TREND

Companies have developed several innovations over the past few years aimed at using AI to assist with detecting and diagnosing heart disease.  

In 2018, Google AI announced that it had successfully predicted cardiovascular problems using images of the retina – a potential major breakthrough.  

A few years later, the FDA approved marketing authorization for AI-enabled cardiac ultrasound software to assist in diagnosis for non-expert providers. And this past month, a study found that a new AI tool may help cardiologists select the best non-invasive diagnostic test.  

ON THE RECORD  

"The takeaway is that we are likely to see more AI use in the practice of medicine as time goes on. It's up to us to figure how to use this in a way that improves care and health outcomes but does not overburden front-line clinicians," said Noseworthy.

 

Kat Jercich is senior editor of Healthcare IT News.
Twitter: @kjercich
Email: kjercich@himss.org
Healthcare IT News is a HIMSS Media publication.

Want to get more stories like this one? Get daily news updates from Healthcare IT News.
Your subscription has been saved.
Something went wrong. Please try again.