Google AI Detects High Blood Pressure Signs From Smartwatch Sensors

Google Research has developed an AI system that can detect signs of high blood pressure using a regular smartwatch, without needing a blood pressure cuff for calibration. The approach uses pulse and motion sensors already built into modern watches. Google says the findings are included in the blood pressure trends feature in the Google Health app, but the method remains a research project and does not replace a diagnosis.

How the AI learns

The study was published in Nature. A neural network learned from nearly 500,000 hours of sensor data by comparing short segments and figuring out which ones belonged to the same person. It picked up typical pulse and heartbeat patterns without any diagnoses to guide it, then averages these patterns over several days and calculates a probability for high blood pressure. Google's health model SensorFM also learns from smartwatch data.

Study results

In a study of 196 people across five US research sites, the watch spotted hypertension about as well as a traditional cuff. It identified 65.8 percent of those with high blood pressure, compared with 55.3 percent for the standard in-office measurement. More than half of people with high blood pressure do not know they have it, according to Google. The goal is to nudge people toward getting checked.

App feature and limits

Google says the findings have been folded into the blood pressure trends feature in the Google Health app. However, the method is still a research project and does not replace a diagnosis. The AI relies on two sensors already built into modern watches, a pulse sensor and a motion sensor.

Sources: The Decoder