
The team developed an app called BiliScreen, and with a smartphone's camera, it uses computer vision algorithms to detect levels of the chemical bilirubin in the whites of a person's eyes. With pancreatic cancer, bilirubin levels start to increase and eventually, it turns the whites of the eye yellow, which is also the case for hepatitis. However, when that yellowing becomes noticeable, the cancer is already very developed. BiliScreen can detect miniscule levels of bilirubin and provide users with an assessment of whether their levels are high enough to indicate possible disease. This is easier and cheaper than a blood test, which is the traditional test for the cancer and can be done before any symptoms start to show.
To take lighting into account, the app can be used with either a special box that blocks out ambient light or paper glasses with colored squares around the edges that the app is calibrated to. With the box, BiliScreen was around 90% as accurate as a blood test in identifying concerning levels of bilirubin in a small, 70-person clinical study.