Nature Medicine: Smart watch electrocardiograms can accurately detect heart failure in non-clinical settings

• Two health technology advancements: an app and back-end infrastructure that lets patients share smartwatch ECG data remotely with their clinicians in a simple and secure way, and modifies a proven 12-lead ECG artificial intelligence (AI) algorithm to enable it to run on
  single-lead watch ECG recording.
  

• An artificial intelligence algorithm applied to the Apple Watch ECG recording successfully identified the patient's weak heart pump
  .
  

• These findings suggest that there may be a relatively inexpensive tool that could be widely used to detect heart failure
  in people outside of the clinical setting.
  

- A study published in Nature Medicine reported the ability
of a smartwatch electrocardiogram to accurately detect heart failure in a non-clinical setting.
Researchers at the Mayo Clinic applied artificial intelligence (AI) to the Apple Watch ECG recordings to identify patients
with weak heart pumps.
Participants in the study remotely recorded their smartwatch electrocardiograms
anytime, anywhere.
Through a smartphone app developed by Mayo Clinic's Center for Digital Health, they regularly automatically and securely upload electrocardiograms to
their electronic health records.

"Currently, we diagnose ventricular insufficiency (weak heart pumps) through echocardiograms, CT scans or MRIs, but these are expensive, time-consuming, and sometimes not possible
.
Paul Friedman, M.
D.
, chair of the Department of Cardiovascular Medicine at the Mayo Clinic in Rochester, said, "Remote diagnosis of weak heart pump function through electrocardiograms recorded by people using consumer devices such as smart watches can identify this potentially life-threatening disease
in a timely and large-scale manner.
" Dr.
Friedman is the senior author
of the study.

People with weak heart pumps may not have symptoms, but this common heart disease affects about 2 percent of the population and 9 percent of people
over the age of 60.
Symptoms may appear when the heart can't pump enough oxygen-rich blood, including shortness of breath, increased heart rate, and swollen
legs.
Early diagnosis is important because, once diagnosed, there are many treatments that can improve quality of life and reduce the risk of
heart failure and death.

Mayo researchers interpreted Apple Watch single-lead ECGs by modifying an algorithm developed earlier for 12-lead electrocardiograms, which have been shown to detect weak heart pumps
.
The 12-lead algorithm for low ventricular ejection fraction was licensed to Anumana, an AI-driven health technology company co-created
by nference and Mayo Clinic.

Although the data are still in their early stages, the improved AI algorithm using single-lead ECG data to detect the area under the curve of the weak heart pump is 0.
88
.
In contrast, the accuracy of this measurement method is as good, if not slightly better
, than a medical treadmill diagnostic test.

"These data are encouraging because they show that digital tools can be convenient, inexpensive and scalable to screen for important diseases
.
Through technology, we can remotely gather useful information about a patient's heart in an accessible way that can meet people's needs," said
Dr.
Zachi Attia, chief AI scientist in the Department of Cardiovascular Medicine at the Mayo Clinic.
Dr.
Attiya is the first author of
the study.

"Building the ability to ingest data from wearable consumer electronics and providing analytics to prevent disease or improve remote health, in the way this study demonstrates, can revolutionize healthcare
.
" Solutions like this not only anticipate and prevent problems, but ultimately help reduce health disparities and burdens on health systems and clinicians," said Bradley Lebovic, MD, medical director of the Mayo Clinic Center for Digital Health and a co-author of the study
.

All 2454 study participants were Mayo Clinic patients
from the United States and 11 countries.
They downloaded an app developed by the Mayo Clinic Center for Digital Health to securely upload their Apple Watch electrocardiograms to electronic
health records.
Between August 2021 and February 2022, participants recorded more than 125,000 previous and new Apple Watch ECGs
in electronic health records.
Clinicians can view all ECG data, including the date and time
recorded, on an AI dashboard built into electronic health records.

About 420 participants had echocardiography — a standard test
that uses sound waves to produce images of the heart — within 30 days of recording their electrocardiograms in the Apple Watch app.
Of these, echocardiography confirmed a low ejection fraction in 16 patients, which provided a comparison
of accuracy.