Pancreatic cancer has a five-year survival rate of just 9% partly because there are not detectable symptoms or noninvasive tools to screen for a tumor. A recent article from UW News says a team at University of Washington is hoping to change that with a new app. The app is called BiliScreen, and it uses a smartphone camera, computer vision algorithms, and machine learning to detect high bilirubin levels in the white of a person’s eye. A buildup of bilirubin in the blood is indicative of jaundice, which is one of the earliest symptoms of pancreatic cancer.
The app is used in tandem with a 3-D printed box that blocks out ambient lighting and paper glasses printed with colored squares to help calibrate color. In the initial clinical study of 70 people, the app correctly identified “cases of concern” 89.7% of the time, compared to the currently used blood test.
“Pancreatic cancer is a terrible disease with no effective screening right now,” said Dr. Jim Taylor, a professor in the UW Medicine Department of Pediatrics whose father died of pancreatic cancer. “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 tat gives them a better chance of survival.”