Oxygen is life, and our bodies need a lot of it to function optimally. However, there are conditions and illnesses such as asthma and Covid-19 which might cause the amount of oxygen in our body to drop below 95% saturation, which is the mark for a healthy individual.
In a hospital, the doctors use pulse oximeters (those clips you put over your fingertip or ear) to monitor oxygen saturation. However, what if there was a way you could monitor your own oxygen saturation in the comfort of your home several times a day without the use of complicated equipment?
That is exactly what the University of Washington and the University of California, San Diego researchers have been working on, showing that smartphones are capable of detecting blood oxygen saturation levels down to 70%, which is also the lowest value that pulse oximeters should be able to measure.
They managed this by asking participants to place their fingers over the camera and flash of a smartphone, which then uses a deep-learning algorithm to decipher the blood oxygen levels. When the researchers artificially brought down the blood oxygen levels of 6 individuals, they were able to correctly predict whether the subject had low blood oxygen 80% of the time.
“With our test, we’re able to gather 15 minutes of data from each subject. Our data shows that smartphones could work well right in the critical threshold range,” explains Jason Hoffman, a UW doctoral student in the Paul G. Allen School of Computer Science & Engineering.
A key benefit of being able to measure blood oxygen levels on a smartphone is that almost everyone has one. “This way you could have multiple measurements with your own device at either no cost or low cost… In an ideal world, this information could be seamlessly transmitted to a doctor’s office. This would be really beneficial for telemedicine appointments or for triage nurses to be able to quickly determine whether patients need to go to the emergency department or if they can continue to rest at home and make an appointment with their primary care provider later,” says Dr Matthew Thompson, professor of family medicine in the UW School of Medicine.
In order to gather the needed data to train and test the algorithm, the researchers made each participant wear a standard pulse oximeter on one finger and then place another finger on the same hand over a smartphone’s camera and flash. This was done on both hands of each participant, at the same time.
“The camera is recording a video: Every time your heart beats, fresh blood flows through the part illuminated by the flash. The camera records how much that blood absorbs the light from the flash in each of the three colour channels it measures: red, green and blue. Then we can feed those intensity measurements into our deep-learning model,” explains Edward Wang, assistant professor at UC San Diego’s Design Lab and the Department of Electrical and Computer Engineering
Despite their success, the team says they still face challenges such as one of their subjects who had thick calluses on their fingers made it difficult for their algorithm to accurately determine their blood oxygen levels. They say their next step is to engage more with people with calluses, as well as people with different skin tones. The team is, however, still very satisfied with the progress that they have made.
“It’s so important to do a study like this. Traditional medical devices go through rigorous testing. But computer science research is still just starting to dig its teeth into using machine learning for biomedical device development, and we’re all still learning. By forcing ourselves to be rigorous, we’re forcing ourselves to learn how to do things right.”