Transforming smartphone sensors into powerful sources of health insights

We are developing sensing technologies to detect vital health information that can work on smartphones around the world. By making health knowledge accessible with devices people already have, we can help expand access to care globally.

Illustration of a phone showing all different types of sensors on it.
Specialised Health Equipment

Access to some health insights still requires specialized equipment

For people to see certain insights about their own health, they often have to travel to a hospital or clinic with specialized equipment, or they must own devices like wearables or home health tools. This burden makes the detection of changes in health and wellness out of reach for many people globally, especially in under-resourced settings.

Smartphone Sensors

Smartphone sensors that can collect and analyze important health signals

Our deep knowledge of the underlying hardware, alongside world-class machine learning expertise, enables our team of researchers, engineers, and clinicians to build AI sensors that give people the information and insights they need to take control of their health. These measurements are clinically validated, but not meant for medical diagnosis or to evaluate medical conditions.

Cough and snore detection  on Pixel devices

Cough and snore detection on Pixel devices

Pixel can help you understand what affects your sleep, like coughing and snoring activity during the night. The feature uses Pixel’s microphone without recording or sharing data with anyone. On the bedtime summary screen, Pixel shows you how long you snored and how many times you coughed while sleeping.

Heart and respiratory rate image

Heart and respiratory rate

Heart rate and respiratory rate are two vital signs commonly used to assess your health and wellness. Using the Google Fit app on Android and iOS, you can measure your heart rate and respiratory rate using just your phone’s camera.

We developed both features — and completed clinical studies to validate them — so they work in a variety of real-world conditions and for as many people as possible. For example, since our heart rate algorithm relies on approximating blood flow from color changes in someone’s fingertip, it has to account for factors such as lighting, skin tone, age and more in order to work for everyone.

Sleep Sensing on Nest Hub

Sleep Sensing uses Motion Sense to analyze how the person closest to the display is sleeping, based on their movement and breathing. Sleep Sensing can also detect sleep disturbances like coughing and snoring or the light and temperature changes in the room, so you can better understand what’s impacting your sleep. 

Sleep Sensing was built with your privacy in mind. Motion Sense only detects motion, not specific bodies or faces, and your coughing and snoring audio data is only processed on the device. You have multiple controls to disable Sleep Sensing features, including a hardware switch that physically disables the microphone. You can review or delete your sleep data at any time, and consistent with our privacy commitments, it isn't used for personalized ads.

Novel research to unlock new insights from privacy-preserving sensors

Cardiovascular diseases are responsible for a large proportion of premature deaths in under-resourced settings. Early detection and intervention are critical, yet many existing risk scores require a physical examination or lab measurements, which can be challenging due to limited accessibility to healthcare and facilities. We developed a deep learning PPG-based risk score to investigate the potential to use the PPG sensing technology that our previous research has made available on most smartphones to enable large-scale screening at low cost. This research sets the technological foundation for further clinical evaluation of the utility of smartphone-based cardiovascular risk assessments in resource-limited regions.