AI researchers at Mayo Clinic use the Apple Watch to detect silent, weakening heart disease

Using simplified ECG data taken from an Apple Watch, researchers at the Mayo Clinic were able to use an artificial intelligence algorithm to spot people whose hearts may be having trouble pumping blood out to the rest of the body. 

The condition—known as low ejection fraction, where a smaller percentage of blood is pushed out of the heart with each beat—is linked with worsening heart failure and can go undetected with no signs or symptoms or be associated with shortness of breath or blood pooling in the legs.

"Left ventricular dysfunction—a weak heart pump—afflicts 2% to 3% of people globally and up to 9% of people over age 60,” said Paul Friedman, M.D., chair of the Department of Cardiovascular Medicine at Mayo Clinic in Rochester, Minnesota.

Researchers at the clinic previously demonstrated that they could use AI to detect cases of low ejection fraction using a hospital-based ECG with 12 leads and multiple electrodes wired to the chest. Now, they’ve shown they can tune the system to get the number of leads down to one.

“It is absolutely remarkable that AI transforms a consumer watch ECG signal into a detector of this condition, which would normally require an expensive, sophisticated imaging test, such as an echocardiogram, CT scan or MRI," Friedman said in a statement.

Participants from 11 countries signed up for the study over email. More than 125,000 ECGs were logged over a period of six months. According to the researchers, the test demonstrated an area under the curve of 0.88, a measure of prediction accuracy about equivalent to a treadmill-based cardiac stress test.

“Advanced diagnostics that once required travel to a clinic can be accurately done, as this Apple Watch ECG study demonstrates, from a patient's wrist whether they live in Brazil or Baton Rouge,” said Bradley Leibovich, M.D., medical director of the Mayo Clinic's Center for Digital Health. The study’s findings were presented at the annual conference of the Heart Rhythm Society.

Previously, the algorithms for analyzing 12-lead ECGs—which have received a breakthrough designation from the FDA and an emergency authorization for use against COVID-19—were licensed by nference and Mayo Clinic to Anumana, an AI developer working on their commercialization.

Mayo Clinic and nference helped launch Anumana in April 2021 alongside a separate company, Lucem Health, a venture between Mayo Clinic and health tech-focused Commure that focuses on algorithms for crunching the numbers from remote patient telemetry devices.