Google Research scientists Paolo Di Achille and Ming-Zher Poh published a study in Nature describing a smartwatch system for hypertension screening. The AI system, named AI-PPG-ACC-HTN, uses photoplethysmography and accelerometer data to detect high blood pressure. The researchers validated the system against 24-hour ambulatory blood pressure monitoring on 196 participants.
The system achieved a sensitivity of 65.8% and specificity of 90.0% for initial hypertension screening. For confirmatory testing in participants with elevated office blood pressure, the system achieved a sensitivity of 78.4% and specificity of 90.9%. The study involved a large training dataset of 492,347 hours of sensor data from 2,109 participants.
The researchers note this is early feasibility research and not indicative of an existing commercial product feature. The system requires further development to improve sensitivity rates. This work suggests a path toward non-invasive blood pressure monitoring on wearable devices. You can monitor your health with more data from your watch in the future.
