Screening for pancreatic cancer with a selfie

University of Washington researchers have developed a smartphone application to aid the early detection of patients at risk of pancreatic cancer.

BiliScreen uses a smartphone camera, computer vision algorithms and machine learning tools to detect increased bilirubin levels in a patient’s sclera.

Increased levels of bilirubin are one of the earliest signs of pancreatic cancer.

In a clinical trial involving 70 patients, the app correctly identified people at risk of the disease 89.7% of the time.

Lead author, Alex Mariakakis, explained that often by the time people are symptomatic with pancreatic cancer, their treatment options are limited.

“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,” he shared.

Similar technology developed by the research team has been used to screen for newborn jaundice by taking a photo of a baby’s skin.

Image credit: Dennis Wise/University of Washington