Apple Watch can be used to detect the most common abnormal heart rhythm when paired with an AI-based algorithm, according to a study conducted through the heartbeat measurement app Cardiogram and the University of California, San Francisco.
Included in the study were 6,158 participants, most of which had normal EKG readings, recruited through the Cardiogram app on Apple Watch. However, 200 of them had been diagnosed with paroxysmal atrial fibrillation, enabling engineers to train a deep neural network to identify these abnormal heart rhythms from Apple Watch heart rate data.
The study began last year to discover whether the Apple Watch could detect an oncoming stroke, quarter of which are caused by an abnormal heart rhythm, according to Cardiogram co-founder and data scientist for UCSF's eHeart study Brandon Ballinger. He added that two-thirds of those types of strokes are preventable with relatively inexpensive drugs.
Cardiogram's deep neural network was tested against 51 in-hospital cardioversions — which is a procedure that restores the heart's normal rhythm — and has reportedly managed to achieve a 97 percent accuracy to find irregular heart activity.
So far this is just a study built on a preliminary algorithm but it holds promise in trying to identify and prevent strokes in the future. Cardiogram plans to further validate its deep neural network "against multiple gold standards, incorporating the results into the Cardiogram app itself, and investigating the ability to detect health conditions beyond atrial fibrillation."
Also worth noting is that Cardiogram is not the only company in this space. The leading player is AliveCor (now Kardia), which on its end has teamed-up with Mayo Clinic on a study involving AI and AliveCor's mobile EKG reader.