A study published in natural medicine reports the ability of a smartwatch ECG to accurately detect heart failure in non-clinical settings. Mayo Clinic researchers applied artificial intelligence (AI) to Apple Watch ECG recordings to identify patients with weak heart pumps. Study participants remotely recorded ECGs from their smartwatch whenever they wanted, wherever they were. Periodically, they uploaded ECGs to their electronic health records automatically and securely through a smartphone app developed by the Mayo Clinic’s Center for Digital Health.
“Currently, we diagnose ventricular dysfunction – a weak heart pump – through an echocardiogram, CT or MRI, but these are expensive, time-consuming and sometimes inaccessible. The ability to diagnose a pump Weak heart rate remotely, from an ECG that a person records using a consumer device, such as a smartwatch, enables rapid identification of this large-scale, life-threatening disease,” says Paul Friedman, MD, chairman of the department of cardiovascular medicine at the Mayo Clinic in Rochester Dr. Friedman is the study’s lead author.
People with a weak heart pump may not have symptoms, but this common form of heart disease affects about 2% of the population and 9% of people over 60. When the heart cannot pump enough oxygen-rich blood, symptoms may develop, including shortness of breath, rapid heartbeat, and swelling in the legs. Early diagnosis is important because once identified, there are many treatments to improve quality of life and decrease the risk of heart failure and death.
Mayo researchers interpreted single-lead ECGs from Apple Watch by modifying an earlier algorithm developed for 12-lead ECGs, which has been shown to detect a weak heart pump. The 12-lead algorithm for low ventricular ejection fraction is licensed from Anumana Inc., an AI-focused health technology company co-founded by nference and Mayo Clinic.
Although the data is early, the modified AI algorithm using single-lead ECG data had an area under the curve of 0.88 to detect weak heart pump. In comparison, this measure of accuracy is as good or slightly better than a medical treadmill diagnostic test.
“These data are encouraging because they show that digital tools allow convenient, inexpensive and scalable screening for important conditions. Using technology, we can remotely gather useful information about a patient’s heart in a way accessible that can meet people’s needs where they are,” says Zachi Attia, Ph.D., senior artificial intelligence scientist in the Mayo Clinic’s Department of Cardiovascular Medicine. Dr. Attia is the first author of the study.
“Building the ability to ingest data from wearable consumer electronics and provide analytical capabilities to prevent disease or improve health remotely in the ways this study demonstrates can revolutionize healthcare. Solutions like this not only predict and prevent problems, but will also ultimately help reduce health disparities and the burden on healthcare systems and clinicians,” says Bradley Leibovich, MD, Medical Director of the Mayo Clinic Center for Digital Health and co-author of the study.
The 2,454 study participants were Mayo Clinic patients from across the United States and 11 countries. They downloaded an app created by the Mayo Clinic Center for Digital Health to securely upload their Apple Watch ECGs to their electronic health records. Participants recorded over 125,000 old and new Apple Watch ECGs in their electronic health records between August 2021 and February 2022. Clinicians had access to all ECG data on an AI dashboard integrated into the electronic health record , including day and time. checked in.
About 420 participants underwent an echocardiogram — a standard test that uses sound waves to produce images of the heart — within 30 days of recording an Apple Watch ECG in the app. Of these, 16 patients had low ejection fraction confirmed by echocardiogram, which provided a comparison for accuracy.
This study was funded by the Mayo Clinic without any technical or financial support from Apple. Drs. Attia and Friedman, along with others, are co-inventors of the low-ejection fraction algorithm licensed from Anumana and could benefit from its commercialization.