Skip to content
Trending storyDeveloping

Google Research reports smartwatch AI detects hypertension signs without cuff calibration

2 articles2 sourcessince Nov 5Last article 2h ago ·

Overview

AISummary of 2 articles

Google Research says a multimodal AI system using smartwatch photoplethysmography and accelerometer data can passively detect signs of hypertension without cuff calibration.

In a 196-participant, five-site study benchmarked against 24-hour ambulatory blood pressure monitoring, the system reached 65.8% sensitivity and 90.0% specificity for initial screening, according to the study published in Nature.

The authors describe the work as early feasibility research, not a standalone diagnosis. They say it does not describe any commercial feature.

Written by AI from the articles below · updated Nov 5, 11:09 AM ET

Check the sources:

Latest developmentNov 5, 11:01 AM ET
Google Research presents a smartwatch AI system for detecting hypertension without cuff calibration

Article timeline

The articles in this story. Times are ET.

Nov 5
  1. Google ResearchOfficial
    Google Research presents smartwatch system detecting signs of high blood pressure

    AIGoogle Research presents a system, published in Nature, that uses standard consumer smartwatch sensors to passively detect signs of high blood pressure. The system is validated against 24-hour ambulatory blood pressure monitoring, the clinical gold standard.

    The AI system uses photoplethysmography (PPG) and accelerometer (ACC) signals recorded using a consumer smartwatch to create waveform embeddings. The waveform embeddings are aggregated over time (days) into a person-level embedding, which, along with a user’s height, are used to predict their blood pressure status.
  2. Google ResearchOfficialPick
    Google Research presents a smartwatch AI system for detecting hypertension without cuff calibration

    AIGoogle Research says a multimodal AI system using smartwatch PPG and accelerometer data can passively detect signs of hypertension without cuff calibration. In a 196-participant, five-site study benchmarked against 24-hour ambulatory blood pressure monitoring, the system reached 65.8% sensitivity and 90.0% specificity for initial screening. The authors state it is early feasibility research and not a standalone diagnosis or a description of any commercial feature.

Heat Trend

Not enough continuous observations to show a trend yet.