The eHeart study at the University of California, San Francisco has shown that a “deep neural network” fed data from the Apple Watch app Cardiogram was 97 percent accurate in detecting the most common type of abnormal heart rhythm, paroxysmal atrial fibrillation. Paroxysmal atrial fibrillation causes about 25 percent of strokes and two-thirds of those strokes are preventable with relatively inexpensive drugs, making this potentially life-saving news. Cardiogram and UCSF plan to further validate the neural network’s findings against external data and incorporate the results into the Cardiogram app itself. The team also intends to see if the system can detect health conditions beyond atrial fibrillation.
Subscribe today so you don’t miss any TidBITS articles!
Every week you’ll get tech tips, in-depth reviews, and insightful news analysis for discerning Apple users. For 28 years, we’ve published professional, member-supported tech journalism that makes you smarter.
Registration confirmation will be emailed to you.