Smartphone Camera, Flash May Help Detect Blood Oxygen Saturation Levels; Enable Patients to Keep an Eye on COVID-19 Symptoms, Too

In a proof-of-principle study, researchers at the University of Washington and the University of California San Diego have found that smartphones can detect blood oxygen saturation levels down to 70 percent.

A EurekAlert! report specified a need for pulse oximeters to be able to gauge, as the Food and Drug Administration recommended.

The technique engages participants by placing their fingers over the flash and camera of a smartphone, which uses a deep-learning algorithm to decipher the levels of blood oxygen.

Then the research team delivered a controlled mixture of oxygen and nitrogen to six subjects to artificially bring their blood oxygen levels down; the smartphone protected whether an individual had low blood oxygen levels most of the time.

Measuring Blood Oxygen Levels Using a Smartphone

According to Jason Hoffman, lead author of the study published in the NPJ Digital Machine Medicine journal, other smartphone apps that are doing this were developed by asking participants to hold their breath.

However, people are getting quite uncomfortable and need to breathe after one minute or so, and that's before their blood oxygen levels have gone down far enough to represent an entire range of clinically relevant data.

Hoffman, a UW doctoral student in the Paul G. Allen School of Computer Science and Engineering, also said, with their test, they can "gather 15 minutes of data" from every subject. Their data reveals that smartphones could work well in the crucial threshold range.

Another advantage of smartphones measuring blood oxygen levels is that nearly everyone has one.

Smooth Data Transmission

This way, co-author Dr. Matthew Thompson, a professor of family medicine at the UW School of Medicine, said one could have multiple measurements with his device at either low cost or no cost.

In an ideal world, such information could be smoothly transmitted to a doctor's office. This would certainly be advantageous for telemedicine appointments or triage nurses to rapidly determine whether a patient needs to go to the emergency department or if he can continue resting at home and make an appointment with his primary care provider later on.

To collect data to train and test the algorithm, the study investigators had each participant wear a standard pulse oximeter on one finger, then place another on the same hand over the camera and flash of a smartphone. Each participant had this same set-up simultaneously on both hands.

How the Cellphone Camera and Flash Function

Describing how the cellphone camera works, senor author Edward Wang, who started this project as a doctoral student studying electrical and computer engineering at UW and is now an assistant professor at the Design Lab and the Department of Electrical and Computer Engineering of UC San Diego said, it is recording a video.

He added that a similar SciTechDaily report said that each time a user's heart beats, fresh blood flows through the part illuminated by the flash.

Meanwhile, Varun Viswanath, the study's co-lead author and a UW alumnus currently a doctoral student advised by Wang at UC San Diego, smartphone light can get scattered by all the other components in the finger. This means there is a lot of noise in the data being looked at.

The co-lead author also said that deep learning is a helpful technique here as it can see such complex and nuanced features and helps find patterns that we would not otherwise be able to see. The researchers hope to continue this study by testing the algorithm on more participants.

Related information about using a smartphone to detect oxygen levels is shown on Sultan Global's YouTube video below:

Check out more news and information on Medicine & Health and Tech & Innovation In Science Times.