- Najja Parker The Atlanta Journal-Constitution
Typically, selfies are used to capture life’s best moments. Now you may be able to use them to detect pancreatic cancer thanks to a new app.
Researchers from the University of Washington have developed BillScreen, an app that scans the disease with just the snap of a photo.
“The problem with pancreatic cancer is that by the time you’re symptomatic, it’s frequently too late,” lead author Alex Mariakakis said in a statement. “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.”
Here’s how it works:
The program uses a smartphone camera, computer vision algorithms and machine learning tools to detect increased bilirubin levels in a person's eye.
Bilirubin is a substance found in bile. Too much of it can cause jaundice, which is a yellow discoloration of the skin and eyes and one of the first symptoms of pancreatic cancer. Doctors usually administer a blood test to identify jaundice.
By snapping pictures of the eye, BiliScreen can calculate bilirubin levels based on the eye’s color information and the wavelengths from the light.
To test out the invention, scientists conducted a study on 70 individuals. The app correctly identified “cases of concern” 89.7 percent of the time compared to the blood tests.
In September, they will present their results at Ubicomp 2017, the Association for Computing Machinery's International Joint Conference on Pervasive and Ubiquitous Computing.
Take a look at the video below to learn more.