Devices & Diagnostics, Hospitals, Startups

Scientists develop app to diagnose jaundice in newborns

As hospitals speed new mothers out the door, one unintended consequence is that infants can […]

As hospitals speed new mothers out the door, one unintended consequence is that infants can develop signs of jaundice after they’re home. That means it then takes more time to diagnose and treat the condition than if it had been caught before leaving the facility. Computer scientists and professors at University of Washington have developed a way to help parents diagnose jaundice through a combination of a mobile app, a smartphone camera and its flash and a color calibration card. It’s called BiliCam, as in bilirubin — the chemical that infants fail to flush from their bodies that causes jaundice.

The team behind the app published its findings in a research paper that it will present next month in Seattle at the Association for Computing Machinery’s International Joint Conference on Pervasive and Ubiquitous Computing.

Here’s a description of how BiliCam works from the University of Washington’s website:

“A parent or health care professional would download the app, place the card on her baby’s belly, then take a picture with the card in view. The card calibrates and accounts for different lighting conditions and skin tones. Data from the photo are sent to the cloud and are analyzed by machine-learning algorithms, and a report on the newborn’s bilirubin levels is sent almost instantly to the parent’s phone.”

The app is also being considered as a way to do initial screening for jaundice to determine if the infant needs a blood test, which is the gold standard for identifying jaundice.

“This smartphone test is really for babies in the first few days after they go home,” said Dr. James Taylor, a professor of pediatrics and medical director of the newborn nursery at UW Medical Center. “A parent or health care provider can get an accurate picture of bilirubin to bridge the gap after leaving the hospital.”

Lilian de Greef and Mayank Goel are PhD students in computer science. Goel’s work is focused on health sensing and interactive devices. Along with Taylor, other university faculty on the team include Dr. James W. Stout, Shwetak N. Patel, and Eric C. Larson.

Shares0
Shares0