iPhoneForums.Net News Team
- Jun 18, 2010
- Reaction score
Tech Crunch reports that a new study conducted by the University of California, San Francisco (UCSF), using the heartbeat measurement app Cardiogram, finds that the Apple Watch is 97% accurate in detecting the most common type of abnormal heart rhythm when paired with an AI algorithm.
The UCSF Health eHeart study featured 6,158 respondents who had signed up via the Apple Watch Cardiogram app. Most of those who took part in the study had normal EKG readings, but 200 of those studied had received a diagnosis of paroxysmal atrial fibrillation (abnormal heartbeat). Engineers then worked on a deep neural network and trained it so that it could identify the abnormal heart rhythms from Apple Watch heart rate data.
The Cardiogram and UCSF study started in 2016 with the aim of finding out if the Apple Watch was able to detect the signs of an oncoming stroke, with Cardiogram co-founder and UCSF eHeart study data scientist Brandon Ballinger saying that more than one quarter of strokes are caused by an abnormal heart rhythm. According to Ballinger, two-thirds of such strokes can be prevented with inexpensive drugs. With more and more older people and others prone to strokes now wearing technology such as the Fitbit or Apple Watch, research such as this could save many lives in the future.
Source: Apple’s Watch can detect an abnormal heart rhythm with 97% accuracy, UCSF study says