
Scientists developed a new method of screening for pancreatic cancer thanks to selfies and a smartphone app.
A team of researchers part of the University of Washington developed a new app which can help screen for pancreatic cancer. It is based on selfies taken with a smartphone, and its detection of jaundice.
This is a yellowing of the eyes and skin caused by the increase of bilirubin in the blood. It is also one of the earliest symptoms of both pancreatic cancer and also other diseases.
Screening for Pancreatic Cancer to Become Easier Thanks to Selfies
Pancreatic cancer is one of the worst types of the worst prognoses of the disease. It usually lacks symptoms, and its number of noninvasive screening tools is very small. Its five-year survival rate is also of just nine percent.
The currently used blood test screening for bilirubin levels is not usually conducted on adults only where there is a serious cause for concern. It also requires access to a health care professional and is inconvenient in frequent screenings.
This new method of screening involves an app called BiliScreen. It makes use of the smartphone’s camera and is based on machine learning tools and computer vision algorithms. Thanks to these, it can detect the increase of bilirubin levels in a person’s sclera or the white part of the eye.
“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,” states Alex Mariakakis, part of the University of Washington’s Paul G. Allen School of Computer Science & Engineering.
The study team conducted a trial to test its app. This involved 70 people who used the BiliScreen app and a 3D printed box which controls the eye’s light exposure.
The test was accurate in identifying pancreatic cancer in 89.7 percent of the cases.
Details on the app and the tests will be presented on September 13 at Ubicomp 2017, the International Joint Conference on Pervasive and Ubiquitous Computing of the Association for Computing Machinery.
Image Source: Pexels