One of the earliest indicators of pancreatic cancer is jaundice, which causes yellowing of a person’s skin and eyes and is caused by a buildup of a substance called bilirubin in the blood. Unfortunately, by the time the jaundice is visible to the naked eye, the cancer has already progressed to an advanced stage. But with a new smartphone app called BiliScreen, jaundice could be detected in the sclera, or whites of the eyes, at a much earlier stage.
BiliScreen uses machine learning tools and computer vision algorithms to detect increased bilirubin levels in the sclera when they’re only minimally elevated. The app requires only a smartphone camera and flash, plus a 3D printed box, similar to the one used for a Google Cardboard headset, to block out ambient light. The researchers developed a computer vision system that automatically isolates the whites of the eyes, then calculates the color information from the sclera, based on the wavelengths of light being reflected and absorbed, and correlates it with bilirubin levels using machine learning algorithms.
In an initial clinical study of 70 people, the researchers found that the app correctly detected elevated bilirubin levels 89.7 percent of the time when using the 3D printed box. They also tried using the app with a pair of paper glasses printed with colored squares to help calibrate color, but the 3D printed box delivered slightly better results.
The study was detailed in a paper entitled “BiliScreen: Smartphone-Based Scleral Jaundice Monitoring for Liver and Pancreatic Disorders,” which you can read here.
“The problem with pancreatic cancer is that by the time you’re symptomatic, it’s frequently too late,” said lead author Alex Mariakakis, a doctoral student at the Paul G. Allen School of Computer Science & Engineering. “The hope is that if people can do this simple test once a month — in the privacy of their own homes — some might catch the disease early enough to undergo treatment that could save their lives.”
BiliScreen is even more effective than BiliCam, however, as the eyes are more sensitive than the skin to changes in bilirubin levels – and color changes in the sclera are consistent across races and skin colors.
“The eyes are a really interesting gateway into the body — tears can tell you how much glucose you have, sclera can tell you how much bilirubin is in your blood,” said senior author Shwetak Patel, the Washington Research Foundation Entrepreneurship Endowed Professor in Computer Science & Engineering and Electrical Engineering. “Our question was: Could we capture some of these changes that might lead to earlier detection with a selfie?”
As it turns out, they could. So while it may sound like clickbait, selfies really may be able to save your life. The next steps in the research involve testing the app on a wider range of people at risk for jaundice and its associated conditions, as well as eliminating the need for accessories such as the 3D printed box.
Co-author Dr. Jim Taylor, a professor in the UW Medicine Department of Pediatrics, lost his father to pancreatic cancer at age 70, so he has a personal stake in finding better screening and treatment tools for the disease.
“This relatively small initial study shows the technology has promise,” he said. “Our goal is to have more people who are unfortunate enough to get pancreatic cancer to be fortunate enough to catch it in time to have surgery that gives them a better chance of survival.”
Authors of the study include Alex Mariakakis, Megan A. Banks, Lauren Phillipi, Lei Yu, James Taylor and Shwetak Patel. It was funded by the National Science Foundation, the Coulter Foundation and endowment funds from the Washington Research Foundation. Discuss in the BiliScreen forum at 3DPB.com.
