- February 13, 2018
The app, dubbed BilliScreen, uses computer vision algorithms and machine learning algorithms to detect jaundice in a photo of a person’s eyes. Specifically, it measures elevated levels of bilirubin in the sclera, the white part of the eye. Jaundice, an early symptom of pancreatic cancer and a number of other diseases, is caused by a buildup of bilirubin.
Bilirubin levels can be measured by a blood test, but this requires a healthcare professional and is inconvenient for frequent testing. The noninvasive BilliScreen could facilitate the screening of individuals at risk of pancreatic cancer.
A user takes a photo of his or her face using a smartphone camera, a pair of special glasses and a 3D-printed box that controls the eye’s exposure to light. In a 70-patient study, BilliScreen “correctly identified cases of concern 89.7% of the time,” compared to the blood test that detects bilirubin. The findings are published in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies.
“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.”
BilliScreen is based on research from the University of Washington’s Ubiquitous Computing Lab, which previously created a smartphone app that detects jaundice in newborns from a photo of their skin. The team plans to improve the device design, aiming to eliminate the need of aids such as the light-controlling box and glasses. They will also test the app on a broader range of people at risk for jaundice and underlying conditions other than pancreatic cancer.
REFERENCE: Fierce BioTech; 29 AUG 2017; Amirah Al Idrus