Deep-learning system uses smartphone camera for heart rate monitoring

A team of medical researchers and engineers at Google Research has developed a way to use the front-facing camera on a smartphone to monitor a patient’s heart rate. The team has published a paper on the technology on the arXiv preprint server.

Tracking a patient’s heart rate over time can reveal clues about their cardiovascular health. The most important measurement is resting heart rate (RHR)—people with an above-normal rate are at a higher risk of heart disease and/or stroke. Persistently high rates, the researchers note, can signal a serious problem.

Over the past several years, personal health device makers have developed wearable external heart monitors, such as necklaces or smartwatches. But these devices are expensive. The researchers have found a cheaper alternative—a deep-learning system that analyzes video from the front-facing camera of a smartphone. The system is called PHRM.

The idea for the system is derived from work by John Poel; he discovered back in the 1940s that the skin changes color slightly during each pulse of blood flow. He went even further by inventing a device that could be used to monitor the heart rate using light beamed and bounced back from the skin, and in so doing invented a new science: photoplethysmography.

Many devices based on Poel’s work have been developed over the years, which has led the team involved in this new study to use the same technology but in a new way—by analyzing the light bounced back when a smartphone is aimed at a person’s face. It measures changes in blood volume, which allows for monitoring both regular heart rate (HR) and RHR.

To ensure that the system works for people of all skin colors, the research team tested and fine-tuned its parameters to account for any skin color. They also extensively tested their system with the assistance of 495 volunteers who provided 225,773 videos of their faces. They followed that up with validation testing courtesy of 185,970 videos provided by 205 people across a wide variety of lighting conditions. The results were comparable to those obtained using traditional devices such as electrocardiographs.

The advantage of the new system is that it does not require any additional equipment—all that is needed is a smartphone with a camera. The development could make heart rate monitoring accessible to billions of people around the world.

© 2025 Science X Network