Better screening tools for all cancers would be great, but one type in particular where it could have a huge impact is pancreatic cancer. The symptoms of this devastating disease don’t reveal themselves until it’s well advanced, and it carries a five-year survival rate of just 5-9%.
Now, University of Washington scientists have developed an app that could allow people to easily detect pancreatic cancer by simply scanning the white part of the eye for one of the disease’s early tell-tale signs.
One of the early signs of pancreatic cancer is jaundice, which is characterized by yellowing of the skin and eyes as a result of the buildup of a substance in the blood known as bilirubin. However, the trouble with bilirubin buildup, other than the fact that it can be an indication of several diseases, is that it can only be detected by blood tests that doctors won’t administer unless there is already cause for concern.
We have already recently seen exciting progress towards a urine test for pancreatic cancer, but this new app would require no bodily fluids at all.
Dubbed Biliscreen, this app uses a smartphone camera along with computer vision algorithms and machine learning to detect increased levels of bilirubin in the white part of the eye, known as the sclera. In adults, the sclera is more sensitive than the skin to elevated bilirubin levels and the University of Washington team hopes that Biliscreen will be able to detect these changes before they become visible to naked eye, when it’s already too late.
Shwetak Patel, the senior author of the study, states that “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?”
The technology was put to the test in a clinical trial that involved 70 people. The app was used in combination with either a special box made to control light exposure or paper glasses to calibrate color. The team found that it was able to detect causes for concern 89.7% of the time.
It works by using the camera and flash to capture an image of the eye, and then computer vision software to isolate the sclera. The app then assesses the wavelengths of light that are being reflected and absorbed by the sclera, calculating color information, and then uses machine learning algorithms to correlate that with bilirubin levels.
Dr. Jim Taylor, co-author of the study and professor in the UW Medicine Department of Pediatrics, explains that “this relatively small initial study shows the technology has promise. Pancreatic cancer is a terrible disease with no effective screening right now. 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.”
Now, the team is looking to build on these exciting early results by testing the app on larger groups of people at risk of jaundice and other related conditions. They are also going to try to make the technology more convenient to use, by possibly removing the need for the box or glasses.
The video below provides and overview of this groundbreaking technology.