Researchers at Rochester, Minn.-based Mayo Clinic developed an AI algorithm and app that can detect a weak heart pump from electrocardiograms recorded on Apple Watch.
To interpret ECG signals generated from the single lead on an Apple Watch, researchers modified a 12-lead algorithm for low ventricular ejection fraction to detect a weak heart pump from electrocardiograms recorded on an Apple Watch.
Here's how they did it:
- In a decentralized, prospective study, Mayo Clinic developed a smartphone app that participants used to send single lead ECGs from their Apple Watch.
- Researchers collected 125,000 Apple Watch EKGs from more than 2,400 participants in 46 U.S. states and 11 countries over the course of six months.
- The app was used to securely send all previous Apple Watch ECG data and additional ones as they were recorded by patients to a Mayo data platform where they were analyzed by the AI algorithm.
- To modify the algorithm, scientists created an adaptation technique that translated the single-lead readings into signals understandable by the algorithm. This allowed the algorithm to work with a single lead watch signal.
"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," said Itzhak Attia, PhD, lead AI scientist in the Department of Cardiovascular Medicine at Mayo Clinic. "AI analysis of the watch ECG is a powerful test to identify a weak heart pump."
The study validated that medically useful information can be obtained by a single-lead watch.