A Smartphone Based App Can Help Detect Jaundice in Babies

A smartphone app developed at University College London (UCL) can accurately identify jaundice in babies by scanning their eyes and could be a lifesaver in resource poor and remote settings.

Jaundice, caused by build-up of bilirubin in the body, is common in babies and normally harmless. However, in severe cases it can be life threatening and result in symptoms such as brain inflammation and seizures. Every year 114,000 newborn deaths can be attributed to severe jaundice, despite it being a treatable condition.

A new study testing the accuracy of the neoSCB app, which is linked to a user’s smartphone camera, in Ghana showed it was able to accurately detect severe jaundice in 94% of the babies tested in the study who were confirmed to have severe jaundice by other methods.

This level of accuracy is similar to that of current screening methods using a transcutaneous bilirubinometer, but the smartphone method is more affordable and accessible. While it is sometimes possible to get an indication of whether babies are jaundiced by looking at the color of the normally white sclera in the eye, this method can be inaccurate and confirmation by a diagnostic device such as a bilirubinometer is currently advised.

“The study shows that the neoSCB app is as good as commercial devices currently recommended to screen for severely jaundiced newborns, but the app only requires a smartphone which costs less than a tenth of the commercial device,” says Terence Leung, an engineer based at UCL who was one of the developers of the app and a co-author on the study describing the work published in Pediatrics.

“We hope that, once rolled out widely, our technology can be used to save the lives of newborns in parts of the world that lack access to expensive screening devices.”

The app was initially tested in a group of 37 babies in London, before being tested more broadly in this study in 336 babies in Ghana. Of those tested, 79 were found to have severe jaundice when tested by other methods. The neoSCB app identified 74 of the 79 correctly as compared to 76 of 79 that were identified by using a transcutaneous bilirubinometer.

More validation work is needed, but the team thinks their technology could be very useful in remote or resource poor settings, such as in rural Africa, where access to smartphones is often good, but more expensive medical devices such as a bilirubinometer are harder to find.

“This app has the potential to prevent death and disability worldwide in many different settings. It will reduce unnecessary hospital visits and potentially empower community health workers and parents to care for newborn babies safely,” says senior study author Judith Meek, also based at UCL, in a press statement.