An initial clinical test study of 70 people found the app and a 3D printed box to control light conditions was able to correctly identify cases of concern nearly 90 per cent of the time when compared with blood tests. Researchers hope it would make testing for the disease much more accessible for the public.
BiliScreen can detect changes in the whites of human's eyes before people can
The findings will be presented at an upcoming computing conference. Developers UbiComp have previously created BiliCam which has been used to detect jaundice in newborn babies by photographing their skin.
Computer science professor and senior author Shwetak Patel said: "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."
"Our question was: Could we capture some of these changes that might lead to earlier detection with a selfie?"
Fellow author Dr Jim Taylor said the small initial study shows "promise."
"Pancreatic cancer is a terrible disease with no effective screening right now," 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."