Smartphone cameras can accurately measure blood oxygen levels

Researchers have shown that smartphone cameras are able to detect blood oxygen saturation levels up to 70%, which is the lowest value Customized pulse oximeter It should be able to measure as recommended by the US Food and Drug Administration.

The proof-of-principle study was conducted by researchers from the University of Washington and the University of California, San Diego and published paper on results in digital medicine npj. The method asks participants to place their finger on the camera and flash a smartphone which is then tasked with decoding blood oxygen levels using an app equipped with a deep learning algorithm.

The study used six participants between the ages of 20 and 34, three of whom were identified as female and three as male. In order to train and test the algorithm, the researchers asked each participant to wear a standard one-finger pulse oximeter and then simultaneously place another finger on the same hand on a smartphone camera and flash.

Blood oxygen levels are measured with a smartphone camera
One way to measure oxygen saturation is to use pulse oximeters – those little clips you put on the tip of your finger (some shown here in gray and blue). In a proof-of-principle study, researchers from the University of Washington and the University of California at San Diego demonstrated that smartphones are able to detect blood oxygen saturation levels in a range similar to independent clips. The technique involves having participants place their fingers on the camera and flash of the smartphone.

“The camera records a video: Every time your heart beats, new blood flows through the part that lights up with the flash,” said senior author Edward Wang, who started the project as a doctoral student at the University of Washington studying electrical and computer engineering and is now an assistant professor in the lab. Design at the University of California, San Diego, Department of Electrical and Computer Engineering.

The camera records how much blood the light from the flash absorbs into each of the three color channels it measures: red, green, and blue. Then we can enter these density measurements into our deep learning model.”

Usually the light of a smartphone is scattered around many components that make up a human finger, which means there is a lot of noise in the data. Deep learning has been used to see noise and help find hard-to-distinguish patterns, co-lead author Varun Viswanath explains.

The team says that when they delivered a controlled mixture of nitrogen and oxygen to six people to artificially lower blood oxygen levels, the smartphone app correctly predicted whether the person had low blood oxygen levels 80% of the time.

“Other smartphone apps have been developed that do this by asking people to hold their breath. But people feel very uncomfortable and have to breathe after a minute or so, before their blood oxygen levels drop enough to represent the full range of clinically relevant data. “. Says a doctoral student at the Paul G. Allen Computer Science and Engineering.

“With our testing, we can collect 15 minutes of data from each subject. Our data shows that smartphones can perform well within the critical threshold range.”

Blood oxygen levels are measured with a smartphone camera

Not only does the method work well, the researchers say, but it also uses a device that everyone already owns that theoretically makes reading blood oxygen at home simple and accessible to nearly everyone.

“This way you can get multiple measurements with your own device either at no cost or at low cost,” says co-author Dr. Matthew Thompson, professor of family medicine at the University of Washington School of Medicine.

“In an ideal world, this information could be seamlessly transmitted to a doctor’s office. This would be really useful for telemedicine appointments or for triage nurses so they can determine if patients need to go to the emergency department quickly or if they can continue to rest at home And make an appointment with your primary care provider at a later time.”

The team hopes to continue the research by expanding the group of users on whom the algorithm was tested.

“It’s very important to do a study like this,” Wang says. “Traditional medical devices are subject to rigorous testing. But computer science research is just in its infancy using machine learning to develop biomedical devices and we are all still learning. By forcing ourselves to be strict, we are forcing ourselves to learn how to do things properly” .

Image credits: Dennis Wise/University of Washington