AI breakthrough using a smartwatch ECG allows for remote diagnosis of weak heart pumps

Researchers applied artificial intelligence to smartwatch ECG recordings to accurately identify patients with weak heart pumps.
Brittney Grimes
An elderly man using a smartwatch to measure his heart rate.
An elderly man using a smartwatch to measure his heart rate.


A smartwatch ECG can precisely detect heart failure when used with artificial intelligence. Researchers have applied artificial intelligence (AI) to a smartwatch ECG to accurately determine heart failure in non-clinical environments. In other words, the patient could use a smartwatch ECG and the AI application to find out if they have a weak heart pump or not. The research team applied AI to Apple watch ECG recordings to identify people with a weak heart pump (also called left ventricular dysfunction).

The study was published today in Nature Medicine.

Checking for heart problems remotely and accurately

Participants in the study recorded their smartwatch ECGs (electrocardiograms, used to measure or detect heart problems) remotely. While they did this, sometimes they would upload the ECGs to their electronic health records automatically using an app created by Mayo Clinic Center for Digital Health in the United States.

The current way to check for heart failure would normally be through getting a CT scan or MRI, which can be costly and prolonged. “Currently, we diagnose ventricular dysfunction―a weak heart pump―through an echocardiogram, CT scan or an MRI, but these are expensive, time consuming and at times inaccessible,” said Dr. Paul Friedman, senior author of the study and chair of the Department of Cardiovascular Medicine at Mayo Clinic in Rochester.

AI and the smartwatch

The innovation within this study is the fact that patients have the capability to diagnose a weak heart pump remotely and from a device that uses artificial intelligence. “The ability to diagnose a weak heart pump remotely, from an ECG that a person records using a consumer device, such as a smartwatch, allows a timely identification of this potentially life-threatening disease at massive scale,” Dr. Friedman continued.

Being able to diagnose oneself could possibly be lifesaving. People with a weak heart pump might not display any symptoms, but this version of heart disease does affect about 2% of the population and 9% of people over the age of 60 years old. When the heart does not pump enough oxygen-rich blood throughout the body, symptoms could occur, which include shortness of breath, swelling in the legs and shortness of breath.

Using AI with the smartwatch is essential because it could allow for early diagnosis. If this type of heart disease is diagnosed early, there are treatments available to minimize the effects of the disease and improve quality of life. Such early diagnosis could also decrease the risks of heart failure or death.

Mayo Clinic research in the U.S. interpreted Apple Watch single-lead ECGs by modifying an algorithm that has been proven before to help detect a weak heart pump. The 12-lead algorithm used in the smartwatch is currently licensed to a company called Anumana, an AI-driven health company, co-created with Mayo Clinic. The newly modified AI algorithm uses single lead ECG data that has an area under the curve of .88 to detect a weak heart pump. Researchers compared this data to a medical treatment diagnostic test, with information taken from the AI being just as accurate, and sometime more accurate, than the test.

“These data are encouraging because they show that digital tools allow convenient, inexpensive, scalable screening for important conditions. Through technology, we can remotely gather useful information about a patient's heart in an accessible way that can meet the needs of people where they are,” said Dr. Zachi Attia, first author of the study and the lead AI scientist in the Department of Cardiovascular Medicine at Mayo Clinic.

The research

There were 2,454 participants in the study from across the U.S. and 11 countries. They downloaded an app created by Mayo Clinic Center for Digital Health to upload their Apple Watch ECGs to their health records. Then, clinicians had access to the data, which consisted of more than 125,000 logins of ECGs that were noted between August 2021 and February 2022. The ECG data was on an AI dashboard built into the health records.

The future

Researchers want this study to eventually be used for diagnosing other diseases, using consumer devices such as the smartwatch along with AI. “Building the capability to ingest data from wearable consumer electronics and provide analytic capabilities to prevent disease or improve health remotely in the manner demonstrated by this study can revolutionize health care,” said Dr. Bradley Leibovich, co-author of the study and the medical director for the Mayo Clinic Center for Digital Health.

Many diseases can be treated if diagnosed earlier, and this study shows the importance of finding a solution for earlier diagnosis and prevention, in this case, using electronics with AI.

Add Interesting Engineering to your Google News feed.
Add Interesting Engineering to your Google News feed.
message circleSHOW COMMENT (1)chevron
Job Board