Apple Watch Detects Heart Condition Accurately, Study Finds

The Apple watch and other wearables can accurately detect the heart condition atrial fibrillation in wearers, according to a new study.

Cardiogram and UC San Francisco published the large peer-reviewed study Wednesday in JAMA Cardiology showing that atrial fibrillation was detected with 97 percent accuracy. The study used a deep learning model called DeepHeart to make the detections. 

The study focused on patients who had a known risk of atrial fibrillation, so it remains to be seen whether the model can detect the condition in patients with no known risk at the same accuracy levels, TechCrunch reported.

Cardiogram said it would conduct more studies going forward.

“Just like Google invests in search quality, we are always going to be investing in clinical research,” Cardiogram co-founder Brandon Ballinger said, TechCrunch reported. An economic analysis also is planned to evaluate whether wearables can improve the cost structure of health care diagnostics, TechCrunch reported. 

“We have to be very careful about false positives and causing distress when it’s really not needed or adding to healthcare costs, for example, because of unnecessary testing,” UCSF cardiologist and study lead Gregory Marcus said, The Washington Post reported, adding that more refinement is needed in the model. 

“But it’ll be coming,” Marcus said. “It’s going to get better, and it’s going to be coming soon. This is the first heads-up: Your watches have the capability of doing this, so it’s coming and it’s theoretically possible.” 

The Washington Post reported Stanford Center for Digital Health Executive Director Mintu Turakhia agreed that AI models and wearables are making incremental progress, similar to self-driving cars.

The Deep Heart algorithm also was used to detect hypertension and sleep apnea in another study.

• Microsoft (Smart)Watch ‘Band’ Beats Apple and Fitbit to Market
• Fitbit New Smartwatch Unveiled; Ionic Retails for $300