Number of words – 333<\/p>\n\n\n\n
Scientists have developed an app that allows people to easily screen for pancreatic cancer and other diseases by just clicking a selfie. One of the earliest symptoms of pancreatic cancer, as well as other diseases, is jaundice, a yellow discolouration of the skin and eyes caused by a buildup of bilirubin in the blood, researchers said. The ability to detect signs of jaundice when bilirubin levels are minimally elevated \u2013 but before they are visible to the naked eye \u2013 could enable an entirely new screening programme for individuals at risk, they said.<\/p>\n\n\n\n
The BiliScreen app, developed by researchers at the University of Washington in the US, uses a smartphone camera, computer vision algorithms and machine learning tools to detect increased bilirubin levels in a person\u2019s sclera, or the white part of the eye. The team developed a computer vision system to automatically and effectively isolate the white parts of the eye, which is a valuable tool for medical diagnostics.<\/p>\n\n\n\n
The app then calculates the colour information from the sclera-based on the wavelengths of light that are being reflected and absorbed\u2014and correlates it with bilirubin levels using machine learning algorithms. To account for different lighting conditions, the team tested BiliScreen with two different accessories: paper glasses printed with coloured squares to help calibrate colour and a three dimensional (3D) printed box that blocks out ambient lighting.<\/p>\n\n\n\n
\u201cPancreatic cancer is a terrible disease with no effective screening right now,\u201d said Jim Taylor, professor at University of Washington. \u201cOur 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,\u201d Taylor added.<\/p>\n\n\n\n
In an initial clinical study of 70 people, the BiliScreen app-used in conjunction with a 3D printed box that controls the eye\u2019s exposure to light-correctly identified cases of concern 89.7 per cent of the time, compared to the blood test currently used.<\/p>\n\n\n\n