Smartphone selfies, app have potential to screen for jaundice

3-D printed box aids test; algorithms, machine learning enable early detection of rising bilirubin levels.


University of Washington researchers have developed an app that enables people to easily screen for jaundice by taking a picture of themselves using a smartphone camera.

The app, called BiliScreen, runs on an Apple iPhone and leverages algorithms and machine learning tools to detect jaundice—an early symptom of pancreatic cancer, hepatitis and other diseases—by providing estimates of bilirubin levels in a person's sclera, or the white part of the eye.

BiliScreen calculates the color information from the sclera based on the wavelengths of light that are being reflected and absorbed, and then correlates it with bilirubin levels using machine learning algorithms.

One of the symptoms of jaundice is a yellow discoloration of the eyes caused by a buildup of bilirubin in the blood. However, the key is to detect color changes in the eye before humans can see them, when bilirubin levels are minimally elevated, according to Alex Mariakakis, a doctoral student at UW’s Paul G. Allen School of Computer Science & Engineering.



The clinical gold standard for measuring bilirubin is through a blood test, according to Mariakakis. Nonetheless, he says an initial clinical study of the app, used by 70 volunteers in conjunction with a 3-D printed box that blocks out ambient lighting, correctly identified cases of concern 89.7 percent of the time, compared with the blood test.

“We roughly had 90 percent accuracy,” observes Mariakakis. “The results we have so far we think are promising.”

Also See: Handheld device facilitates cervical cancer screenings

In the clinical study, researchers tested BiliScreen with two different accessories: the 3-D printed box and paper glasses printed with colored squares to help calibrate color. What they found was that using the app with the box accessory generated slightly better results.

“We are working on trying to remove in the future the need for any of those accessories,” adds Mariakakis.

The genesis for BiliScreen was BiliCam, a smartphone app that screens for newborn jaundice by taking a picture of a baby’s skin, which was previously developed by UW’s Ubiquitous Computing Lab. But, in the case of adults, Mariakakis says the whites of the eyes are more sensitive than skin to changes in bilirubin levels. In addition, he notes that changes in the sclera are more consistent across all races and ethnicities versus skin color. As a result, researchers decided to focus on the eyes.

Going forward, Mariakakis and his team are looking to conduct a larger controlled study of the app. If that goes well, researchers intend to “start conversations” with the Food and Drug Administration about regulatory clearance, he concludes, emphasizing that BiliScreen is not yet publicly available.

More for you

Loading data for hdm_tax_topic #better-outcomes...