Researchers at the Mayo Clinic have created an artificial intelligence algorithm that can analyze single-lead ECG readings taken by the Apple Watch to help patients detect whether they could possibly have a weak heart pump, according to research data that was presented at the Heart Rhythm Society conference on Sunday, May 1.
Left ventricular dysfunction, also known as a weak heart pump, affects 2% to 3% of people worldwide, and up to 9% of individuals over 60 years old. Just like atrial fibrillation, another heart problem that the Apple Watch can detect, a weak heart pump may have no symptoms at all. It can also be accompanied by other symptoms including leg swelling, racing heart beats or shortness of breath.
Paul Friedman, chair of the Department of Cardiovascular Medicine at Mayo Clinic in Rochester, Minnesota, said that 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.”
Dr. Paul Friedman discusses in a video wherein Mayo researchers use AI to detect a weak heart pump via a patient’s Apple Watch ECG readings.
The ECG feature on the Apple Watch is a single-lead ECG, which requires users to place their finger on the Apple Watch digital crown for 30 seconds. Results are uploaded to the Apple Health app and can be shared with medical professionals. Mainly the ECGs are designed to help detect atrial fibrillation, but ECG functions and other Apple Watch features are also being studied in the detection of other conditions.
On the other hand, a standard ECG uses 12 electrode leads strategically placed on a person’s arms, legs and chest to create a tracing used to evaluate the electrical signals of the heart.
To interpret ECG signals generated from the single lead on an Apple Watch, researchers modified an established 12-lead algorithm for low ventricular ejection fraction — the weak heart pump — that is licensed to Anumana Inc., an AI-driven health technology company, by nference and Mayo Clinic.
The study involved 125,610 ECGs collected over a period of six months across 46 states and 11 countries. Each person submitted several ECGs, and the cleanest readings were used for the algorithm. Hundreds of the participants underwent clinical testing to measure pump strength, and that data was used to determine whether the Apple Watch could detect an issue.
“Approximately 420 patients had a watch ECG recorded within 30 days of a clinically ordered echocardiogram, or ultrasound of the heart, a standard test to measure pump strength. We took advantage of those data to see whether we could identify a weak heart pump with AI analysis of the watch ECG. While our data are early, the test had an area under the curve of 0.88, meaning it is as good as or slightly better than a medical treadmill test. AI analysis of the watch ECG is a powerful test to identify a weak heart pump,” says Dr. Itzhak Zachi Attia, Ph.D., the lead AI scientist in the Department of Cardiovascular Medicine at Mayo Clinic.
“This test is the first step, as it demonstrates we can get medically useful information from a single-lead watch. Our next steps include global prospective studies to test this prospectively in more diverse populations and demonstrate medical benefit. This is what the transformation of medicine looks like: inexpensively diagnosing serious disease from your sofa,” says Dr. Friedman.