BiliScreen is a software application that has been developed to aid in the diagnosis and treatment of pancreatic cancer. Its creators have been the boys of Ubuquitous Computing Lab In order to develop it, they have had to use different machine learning algorithms capable of detecting whether or not a person can suffer from this type of cancer.
As its developers have commented, apparently the BiliScreen algorithms are capable of, with a simple photo, measure a person's levels of bilirubin in the white area of the eye. It is precisely in this area where a large accumulation occurs if a person can suffer from pancreatic cancer.
BiliScreen, a very simple software that can save many lives
Tell you that this system is not only an application that you can install on your smartphone, but it also includes a light-emitting diode. Thanks to this, the user only has to take a photo of their face using a pair of special glasses and a frame made by 3D printing that blocks light and allows the application to operate in optimal conditions.
In the first studies carried out where BiliScreen has been used, apparently the application was capable of detecting correct cases of pancreatic cancer in 89,7%. As you have commented Alex mariakakis, PhD student in Computer Science and Engineering at Paul G. Allen School:
The problem with pancreatic cancer is that it is often too late to treat it. 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 life-saving treatment.