New Imaging Software Accurately Diagnoses Jaundice

If treatment is deemed necessary, an Arduino (Somerville, MA, USA) Uno microcontroller is used to drive a blue phototherapy LED that oxidizes bilirubin to biliverdin.

The system was tested at an intensive care unit (ICU) in Mosul (Iraq), on 20 newborns diagnosed with jaundice; a second data set captured 16 images of newborns, five of whom were healthy, and the remainder jaundiced. The system was also successfully tested on four manikins with white and brown skin colors, with and without jaundice pigmentation. All test showed the camera system was accurate in detecting jaundice, easy to implement, and affordable. The study was published on October 8, 2021, in Designs.

“Using image processing techniques extracted from data captured by the camera, we can cheaply and accurately screen newborns for jaundice in a non-invasive way, before taking a blood test,” said senior author Professor Javaan Chahl, PhD, of UNISA. “When the bilirubin levels reach a certain threshold, a microcontroller triggers blue LED phototherapy and sends details to a mobile phone. This can be done in one second, literally, which can make all the difference in severe cases, where brain damage and hearing loss can result if treatment is not administered quickly.”

Neonatal jaundice is a yellowing of the skin and other tissues of a newborn infant as a result of a bilirubin level higher than 5 mg/dL. The jaundiced newborns have an apparent icteric sclera and yellowing of the face, extending down onto the chest. The condition is common, affecting over half (50–60%) of all neonates in the first week of life. Prolonged hyperbilirubinemia can result into chronic bilirubin encephalopathy (kernicterus). Treatment includes phototherapy using a blue light at a wavelength of 420-448 nm.

Related Links:
University of South Australia
Middle Technical University