AI transforms smartwatch ECG signal into heart failure diagnostic tool

Research published in natural medicine We report the ability of a smartwatch ECG to accurately detect heart failure in a nonclinical setting.researchers in mayo clinic Applying Artificial Intelligence (AI) to Apple Watch electro-cardiogram Records to identify the patient weak heart pumpStudy participants remotely recorded ECGs on smartwatches from anywhere at any time. At regular intervals, they automatically and securely uploaded their ECGs to their electronic medical records via a smartphone app developed by the Center for Digital Health at the Mayo Clinic.

“Now we are diagnosing ventricular dysfunction – through a weak heart pump echocardiogram, CT scans or MRIs, but these are expensive, time-consuming and sometimes inaccessible. The capability enables timely identification of this potentially life-threatening disease on a large scale. ” Paul Friedman, MD, Chief of Cardiology at the Mayo Clinic in Rochester. Dr. Friedman is the senior author of this study.

People with weak heart pumps may not have any symptoms, but about 2% of the population and 9% of people over the age of 60 have this common heart condition. Shortness of breath, increased heart rate, swollen legs. Early diagnosis is important. Once identified, there are many treatments available to improve quality of life and reduce the risk of heart failure and death.

Mayo researchers modified a previous algorithm developed for 12-lead ECGs to interpret single-lead ECGs on the Apple Watch. Proven to detect weak heart pumpsThe 12-lead algorithm for low ventricular ejection fraction is Anumana Co., Ltd.an AI-driven health tech company co-created by inference and Mayo Clinic.

Although the data are early, the modified AI algorithm using single-lead ECG data had an area under the curve of 0.88 for detecting weak heart pumps. By comparison, this measure of accuracy is the same or slightly better than the medical treadmill diagnostic test.

“These data are encouraging because they show that digital tools enable convenient, inexpensive and scalable screening of important conditions. It can be collected remotely in an accessible way that meets the needs of people in the world.” Dr. Zachi Attia, chief AI scientist in the Department of Cardiovascular Medicine at the Mayo Clinic. Dr. Attia is the lead author of this study.

“This research-proven method will revolutionize healthcare by building capabilities that ingest data from wearables and deliver analytics to remotely prevent disease and improve health. “Such solutions will not only allow us to predict and prevent problems, but ultimately help reduce health disparities and burdens on healthcare systems and clinicians.” increase. Bradley Leibovich, M.D.Medical Director of the Mayo Clinic Center for Digital Health and co-author of the study.

All 2,454 study participants were Mayo Clinic patients in the United States and 11 countries. I downloaded an app created by the Mayo Clinic Digital Health Center to securely upload her ECG from my Apple Watch to my electronic medical record. Participants recorded over 125,000 previous and new Apple Watch ECGs into their electronic health records between August 2021 and February 2022. The clinician had access to view all his ECG data on an AI dashboard embedded in the electronic health record. Recorded.

Approximately 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 those, 16 patients had a low ejection fraction confirmed by echocardiography, providing a comparison of accuracy.

This research was funded by the Mayo Clinic without technical or financial support from Apple. Doctor. Attia and Friedman, like others, co-invented the Anumana-licensed low ejection fraction algorithm and could benefit from its commercialization.