Respiratory conditions such as COVID-19 impair the body’s ability to draw oxygen from the lungs, which is why patients’ blood oxygen levels often need to be checked. New research now suggests that people could track these levels at home, using their smartphones.
Usually, blood oxygen saturation is monitored using a device called a pulse oximeter, which is clipped onto a finger or earlobe. These tools are usually applied and monitored by trained technicians in hospitals or clinics. Oximeters connected to the smartphone do exist, but they are one more item that home users should purchase.
In search of a simpler and less expensive alternative, scientists from the University of Washington and the University of California at San Diego have developed an experimental application. They started with six volunteers between the ages of 20 and 34 – three men, three women, one of whom was African American and the others were Caucasian.
To train the deep learning-based algorithm used by the app, four of these people wore a standard oximeter on one finger and placed another finger on the same hand above the camera lens and flash. smartphone camera. Over a period of 15 minutes, they breathed in a mixture of oxygen and nitrogen, to slowly lower their blood oxygen levels.
As they did, the phone recorded a flash-lit video of blood flowing in and out of their finger. The app continuously analyzed the amount of light absorbed by the blood, in the green, red and blue color channels. The amount absorbed varied with the amount of oxygen in their blood.
When the blood oxygen readings obtained by the oximeter were compared to the light intensity measurements from the phone, it was possible to determine which specific readings corresponded to which specific light measurements. The app was therefore able to learn the amount of oxygen present in the blood at any given time, based on the amount of light absorbed by the blood.
When the app was then tested on the six volunteers, it was found to be able to measure blood oxygen levels up to 70%, which is the lowest value that commercial oximeters have to measure. In contrast, a healthy person should have a blood oxygen level of at least 95% and generally requires medical attention if that level drops below 90%.
In its current form, the app is able to accurately spot low levels 80% of the time. It is believed that this number should improve significantly as the technology develops, which will involve training the application on a much larger data set.
“That way, you could have multiple measurements with your own device for free or at low cost,” said Dr. Matthew Thompson of the University of Washington, co-author of a paper on the research. “In an ideal world, this information could flow seamlessly to a doctor’s office. It would be really beneficial for telemedicine appointments or for triage nurses to be able to quickly determine if patients need to go to the ER. or if they can continue to stay at home.”
The article was recently published in the journal npj Digital Medicine.
Source: University of Washington