Google smartwatch AI spots high blood pressure without a cuff
Google Research has trained an AI that can flag signs of high blood pressure from an ordinary smartwatch, without a cuff for calibration. The model uses two sensors already in modern watches—a pulse sensor and a motion sensor—and the work was published in Nature. A neural network learned from nearly 500,000 hours of sensor data by comparing short segments and inferring which belonged to the same person, picking up typical pulse and heartbeat patterns without diagnoses as labels. It then averages those patterns over several days and estimates a probability of hypertension. Google’s health model SensorFM likewise learns from smartwatch data.
In a study of 196 people at five U.S. research sites, the watch identified 65.8 percent of those with high blood pressure, versus 55.3 percent for a standard in-office cuff measurement. Google says the findings are already in the blood pressure trends feature of the Google Health app, but the method remains a research project and does not replace a diagnosis. The aim is to prompt people to get checked: Google notes that more than half of people with high blood pressure do not know they have it.
Continue in the app — vote & join in ➔