Google Research has developed an AI that can detect signs of high blood pressure using a regular smartwatch, without a blood pressure cuff for calibration. The system uses two sensors already built into modern watches: a pulse sensor and a motion sensor, according to a Google blog post. The study was published in Nature.
The AI is a neural network trained on nearly 500,000 hours of sensor data. It learned by comparing short segments of data and identifying which segments belonged to the same person. It picked up typical pulse and heartbeat patterns without any diagnoses to guide it. The system then averages these patterns over several days and calculates a probability of high blood pressure. Google's health model SensorFM also learns from smartwatch data.
In a study of 196 people across five US research sites, the watch identified 65.8 percent of people with high blood pressure. The standard in-office cuff measurement identified 55.3 percent, according to the report. The source describes the watch as performing about as well as a traditional cuff.
Google says the findings have been incorporated into the blood pressure trends feature in the Google Health app. The source states the method is still a research project and does not replace a diagnosis. Google's stated goal is to encourage people to get checked. According to Google, more than half of people with