Wearables can help predict hypertension, sleep apnea

Tuesday, November 14, 2017

SAN FRANCISCO – Off-the-shelf wearables and a multi-task deep learning algorithm are “surprisingly good” predictors of hypertension and sleep apnea, researchers at the University of California at San Francisco have found. “Whether such (devices) can provide durable and portable predictions for these conditions in other study samples is worth pursuing,” they wrote. Wearables and deep learning algorithms use PPG sensors and accelerometers to determine heart rate variability and activity patterns, which have been associated with incident hypertension, diabetes and sleep apnea. The results were not statistically significant for diabetes.