Google's AI detects high blood pressure from a regular smartwatch without a cuff
Reported by Medical Xpress, jetstream.blog and The Decoder3 sources ↓
Google Research developed an AI that uses a smartwatch’s pulse and motion sensors to identify signs of high blood pressure. In a study of 196 people, it identified a higher share of people with high blood pressure than an in-office measurement; Google says the method is still research, not a diagnosis.
Key points
- The AI identified 65.8% of participants with high blood pressure, versus 55.3% for an in-office measurement
- The study included 196 people at five US research sites
- Google says the method has been folded into the Google Health app’s blood pressure trends feature
- Google says the method remains a research project and does not replace a diagnosis
Sources
- Medical XpressRead ↗AI-powered smartwatch detects high blood pressure with sensitivity similar to office screening
- jetstream.blogRead ↗Google Announces New AI Technology “AI-PPG-ACC-HTN” to Detect Signs of Hypertension on Smartwatches
- The DecoderRead ↗Google's AI detects high blood pressure from a regular smartwatch without a cuff
Details
The study, published in Nature, tested a system that uses pulse and motion sensors already found in modern smartwatches. It estimates the probability of high blood pressure by averaging sensor patterns collected over several days; the watch does not need cuff-based calibration, according to The Decoder.
The neural network was trained on nearly 500,000 hours of sensor data, learning patterns without diagnoses as training labels. Google says the findings have been incorporated into the blood pressure trends feature in its Health app, but the method remains a research project and is not a diagnosis.
Written from coverage as of
Images
- The Decoder
Stocks in this story
Change since open: 20 Nov to 21 Nov 2026
Last refresh