Experiments show that a smartphone camera can provide you with an important health metric

There are different ways to read your heart rate. Most smartwatches from Apple, Samsung, Google, and others give you a real-time reading of how many times your heart beats in a minute. Another device you can buy, a pulse oximeter, gives you a reading when you press a spring-loaded hinge, place your finger in the opening, and close the clip securely.

Currently, smartwatch users can get real-time heart rate readings on their wrist

With a smartwatch, all you have to do is wear the device and tap a button before the reading appears within seconds. A good resting heart rate is 60 to 100 beats per minute (bpm), although a heart rate of 50 bpm to 70 bpm indicates optimal cardiac efficiency.

A completely non-technical way to find your heart rate is to place the tips of your index and middle fingers on your wrist, just below the base of your thumb. Count the beats for 15 seconds and multiply by four to get your beats per minute. For the record, your maximum BPM is 220 minus your age.

Using smartphones to monitor users’ heart rate could save more lives than smartwatches

In its statement, Google said, “Smartphones present a unique opportunity to expand access to health monitoring – today, around five billion people already own a device with powerful sensors capable of monitoring their health.” In 2022, Google showed how phone owners could place a finger on their handset’s camera to measure heart rate on demand.

Clips of the user’s face allow the PHRM to estimate HR and daily RHR. | Image courtesy of Google

Called Passive Heart Rate Monitoring (PHRM), the system uses a smartphone’s front-facing selfie camera to monitor changes in the skin as blood flows through the body. You can’t see the changes with the naked eye, but you can detect it with a video captured in the first few seconds after the Face Unlock process.

Eight-second facial video clips powered by a neural network can estimate users’ heart rate

Deep learning is used in video to estimate HR and RHR close to the numbers obtained by ECG and wearable device, respectively. Software developed by Google processes 8-second facial video clips and runs them through a neural network to predict human presence. These forecasts are consolidated within a day. With PHRM, HR and RHR can be calculated in the background during normal smartphone use.

While using smartphones to track users’ heart rate has been around for a few years, Google’s approach is different because it doesn’t require users to initiate the process. Google’s system, as mentioned earlier, uses the selfie camera during normal phone use to estimate a user’s resting heart rate over time.

Google trained the system using 350,000 video clips taken by nearly 700 test participants. Because dark skin can make it difficult to take camera-based blood flow measurements, Google used a variety of test subjects.

Still need to work

To test the system in the real world outside the controlled environment of a lab, Google had participants use their own phones for a week while wearing ECG equipment and a Fitbit tracker. Google’s system is said to continue to perform well.

There is still work to be done. Although the system provides accurate measurements for people with darker skin, these measurements are difficult to collect. Errors in readings were found to occur when subjects spoke or moved their heads.

Once Google gets rid of the wrinkles, smartphones will become a widely used health tool. Because more people use smartphones than smartwatches, Google’s system will enable many more people to get health-related readings from their phones than the number who receive such data from their smartwatches. Privacy can be ensured by using facial recognition biometrics.