Skip to content

  • Projects
  • Groups
  • Snippets
  • Help
    • Loading...
    • Help
    • Submit feedback
    • Contribute to GitLab
  • Sign in / Register
B
bloodvitals-spo29193
  • Project
    • Project
    • Details
    • Activity
    • Cycle Analytics
  • Issues 17
    • Issues 17
    • List
    • Board
    • Labels
    • Milestones
  • Merge Requests 0
    • Merge Requests 0
  • CI / CD
    • CI / CD
    • Pipelines
    • Jobs
    • Schedules
  • Wiki
    • Wiki
  • Snippets
    • Snippets
  • Members
    • Members
  • Collapse sidebar
  • Activity
  • Create a new issue
  • Jobs
  • Issue Boards
  • Marjorie Bevins
  • bloodvitals-spo29193
  • Issues
  • #14

Closed
Open
Opened Nov 13, 2025 by Marjorie Bevins@marjoriebevins
  • Report abuse
  • New issue
Report abuse New issue

A Smartphone’s Camera and Flash might help People Measure Blood Oxygen Levels At Home


First, pause and take a deep breath. After we breathe in, our lungs fill with oxygen, which is distributed to our purple blood cells for transportation throughout our our bodies. Our our bodies want plenty of oxygen to function, and wholesome folks have at least 95% oxygen saturation all the time. Conditions like asthma or COVID-19 make it more durable for bodies to absorb oxygen from the lungs. This leads to oxygen saturation percentages that drop to 90% or below, a sign that medical attention is needed. In a clinic, medical doctors monitor oxygen saturation utilizing pulse oximeters - these clips you place over your fingertip or ear. But monitoring oxygen saturation at dwelling a number of occasions a day could help patients keep an eye on COVID signs, for monitor oxygen saturation example. In a proof-of-principle research, monitor oxygen saturation University of Washington and University of California San Diego researchers have shown that smartphones are capable of detecting blood oxygen saturation levels right down to 70%. This is the bottom worth that pulse oximeters ought to be able to measure, as advisable by the U.S.


Food and Drug Administration. The method entails members putting their finger over the camera and flash of a smartphone, which uses a deep-studying algorithm to decipher the blood oxygen levels. When the group delivered a managed mixture of nitrogen and oxygen to six topics to artificially deliver their blood oxygen ranges down, the smartphone correctly predicted whether or BloodVitals wearable not the subject had low blood oxygen ranges 80% of the time. The crew revealed these results Sept. 19 in npj Digital Medicine. "Other smartphone apps that do this were developed by asking folks to carry their breath. But folks get very uncomfortable and have to breathe after a minute or so, and that’s earlier than their blood-oxygen levels have gone down far enough to represent the total range of clinically related data," mentioned co-lead author Jason Hoffman, a UW doctoral pupil in the Paul G. Allen School of Computer Science & Engineering. "With our take a look at, we’re ready to gather 15 minutes of data from every topic.


Another good thing about measuring blood oxygen levels on a smartphone is that nearly everyone has one. "This means you can have multiple measurements with your individual machine at both no value or low price," stated co-author Dr. Matthew Thompson, professor of household medicine in the UW School of Medicine. "In a perfect world, this data might be seamlessly transmitted to a doctor’s office. The team recruited six participants ranging in age from 20 to 34. Three identified as feminine, three identified as male. One participant recognized as being African American, while the remainder recognized as being Caucasian. To assemble data to train and BloodVitals experience check the algorithm, the researchers had every participant wear an ordinary pulse oximeter on one finger and then place another finger on the same hand over a smartphone’s camera and flash. Each participant had this similar arrange on both fingers simultaneously. "The camera is recording a video: Every time your coronary heart beats, fresh blood flows by way of the part illuminated by the flash," said senior monitor oxygen saturation creator BloodVitals SPO2 Edward Wang, who began this project as a UW doctoral scholar finding out electrical and laptop engineering and is now an assistant professor at UC San Diego’s Design Lab and the Department of Electrical and Computer Engineering.


"The camera data how a lot that blood absorbs the sunshine from the flash in each of the three coloration channels it measures: crimson, inexperienced and blue," said Wang, who also directs the UC San Diego DigiHealth Lab. Each participant breathed in a controlled mixture of oxygen and nitrogen to slowly reduce oxygen ranges. The process took about 15 minutes. The researchers used knowledge from 4 of the members to practice a deep learning algorithm to pull out the blood oxygen levels. The remainder of the information was used to validate the tactic and then test it to see how nicely it performed on new topics. "Smartphone light can get scattered by all these other elements in your finger, which implies there’s a variety of noise in the data that we’re looking at," said co-lead writer Varun Viswanath, monitor oxygen saturation a UW alumnus who is now a doctoral scholar suggested by Wang at UC San Diego.

Assignee
Assign to
None
Milestone
None
Assign milestone
Time tracking
None
Due date
No due date
0
Labels
None
Assign labels
  • View project labels
Reference: marjoriebevins/bloodvitals-spo29193#14