Mayo Clinic-Developed AI Algorithm Can Detect Weak Heart Function

Mayo Clinic researchers have created an artificial intelligence (AI) algorithm that uses single-lead Apple Watch electrocardiogram signals to detect a weak heart pump, specifically low ventricular ejection fraction. 

Typically, an ECG uses 12 electrode leads placed on the chest, arms, and legs. Although effective, researchers wanted to develop a more accessible resource to identify heart function patterns.

Itzhak Zachi Attia, PhD, the lead AI scientist in the department of cardiovascular medicine at Mayo Clinic, adapted the AI algorithm from a 12-lead ECG algorithm that was awarded breakthrough device designation by the Food and Drug Administration in 2019.

To test the new algorithm, Attia led a study with participants from 46 states and 11 countries. The research team worked with the Mayo Clinic Center for Digital Health to create a smartphone app that 2,454 patients used to record Apple Watch ECGs.

Researchers collected 125,610 ECGs, with the average patient using the app twice a month over the six-month study period.

"Approximately 420 patients had a watch ECG recorded within 30 days of a clinically ordered echocardiogram, or ultrasound of the heart, a standard test to measure pump strength,” said Attia in the press release. “We took advantage of those data to see whether we could identify a weak heart pump with AI analysis of the watch ECG. While our data are early, the test had an area under the curve of 0.88, meaning it is as good as or slightly better than a medical treadmill test. AI analysis of the watch ECG is a powerful test to identify a weak heart pump."

The new algorithm is also a step toward developing more reliable remote patient monitoring methods.

"This test is the first step, as it demonstrates we can get medically useful information from a single-lead watch. Our next steps include global prospective studies to test this prospectively in more diverse populations and demonstrate medical benefit. This is what the transformation of medicine looks like: inexpensively diagnosing serious disease from your sofa," said Paul Friedman, MD., chair of the department of cardiovascular medicine at Mayo Clinic, in the press release.

Research has shown that AI technologies can be successful in improving patient care.

In April, Yale School of Medicine researchers created an AI model that used ECG images to identify heart rhythm disorders. Researchers found that the model could identify heart rhythm problems, partly by pinpointing patterns that the human eye neglects.

Further, Google recently shared details regarding new AI tools it plans to develop to improve cardiovascular and maternal health. One of the tools will use photos of eye interiors to establish potential relationships with cardiovascular risk factors.