Abnormal heart rhythm detection with 97% accuracy by Apple’s Watch

Cardiogram is a heartbeat measurement app in IOS which measures the abnormal heart rhythm with 97% accuracy in Apple Watch combined with AI-based algorithm. its proved in the study of conducting heartbeat measurement app Cardiogram and the University of California, San Francisco.

The study involved 6,158 participants recruited through the Cardiogram app on Apple Watch. Among them most of the participants in the UCSF Health eHeart study had normal EKG readings. However, 200 of them had been diagnosed with paroxysmal atrial fibrillation (abnormal heartbeat). Then engineers trained a deep neural network to identify these abnormal heart rhythms from Apple Watch heart rate data.

In 2016 Cardiogram began the study with UCSF to discover  that the Apple watch could detect the upcoming stroke. Quarter of strokes are caused by an abnormal heart rhythm. So far this is just a study built on a preliminary algorithm but it holds promise in trying to identify and prevent stroke in the future. This study would save many lives. Atrial fibrillation, the most common abnormal heart rhythm, causes 1 in 4 strokes. Ballinger says two-thirds of those types of strokes are preventable with relatively inexpensive drugs. Most of the peoples started to use wearable technology such as Fitbit or the Apple Watch to prevent strokes and to stay healthy.

Apple watch

In the past few years mobile EKG readers have also made great strides . The Mayo Clinic is also involved in this EKG readers, which sticks onto the back of a smartphone and we can use the Kardia app (for both android and IOS) to determine abnormal heart rhythm, and determined it was as good as other EKG devices used in the hospitals. The Mayo Clinic felt so strongly about this study it invested in AliveCor’s latest $30 million round. In the meantime, Cardiogram and UCSF will continue its eHealth study and plan to further validate its deep neural network.



Leave a Reply

Your email address will not be published. Required fields are marked *

Please wait...

Subscribe us

Enter your email address to subscribe to this blog and receive notifications of new posts by email.