A study conducted through heartbeat measurement app Cardiogram and the University of California, San Francisco, shows the Apple Watch is approx 97 percent accurate in detecting an abnormal heart rhythm when paired with an AI-based algorithm.
Cardiogram began the study with UCSF last year to discover whether the Apple Watch could detect an oncoming stroke. About a quarter of strokes are caused by an abnormal heart rhythm, according to Brandon Ballinger,, Cardiogram co-founder and data scientist for UCSF’s eHeart study.
The study involved 6,158 participants recruited through the Cardiogram app on Apple Watch. 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 (an abnormal heartbeat). Engineers then trained a deep neural network to identify these abnormal heart rhythms from Apple Watch heart rate data.
As of today, Cardiogram says its algorithm can almost always successfully determine when a patient is in atrial fibrillation.
In order to validate the model, we obtained gold-standard labels of atrial fibrillation from cardioversions. In a cardioversion, a patient experiencing atrial fibrillation is converted back to normal sinus rhythm, either chemically or with a shock to the heart. 51 patients at UCSF agreed to wear an Apple Watch during their cardioversion.
We obtained heart rate samples before the procedure, when the patient was in atrial fibrillation, and after, when patient’s heart was restored to a normal rhythm. On this validation set, our model performed with an AUC of 0.97, beating existing methods.
Cardiogram plans to put in additional work before using its algorithm to start notifying Cardiogram users of arrhythmias. The company needs to conduct further testing to make sure the algorithm works in a variety of conditions and it needs to work on scaling it so it can be used continuously by all Cardiogram users.