The curse of cancer has consumed millions of people worldwide, and it continues to be the second leading cause of death in the US. Most of the times, cancer becomes incurable only because it is diagnosed at a later stage. Among all the forms of cancer, pancreatic cancer is one of the most difficult ones to diagnose. Patients seek help at a point when the tumor becomes beyond removable. That is one of the reasons that the survival rate for such patients is extremely low.
In many cases, Jaundice is an early sign of this disease leading to discoloration of skin and eyes. It is caused when the cancerous growth in the pancreas obstructs the bile duct, thus building up bilirubin in the blood. The discoloration is visible to the naked eye only when it has reached severe stages. Researchers at the University of Washington have proposed the idea of using a smartphone camera for detecting the bilirubin levels in humans.
Researchers have developed the smartphone app by the name of ‘BiliScreen’ that takes a picture of user’s eye with the camera and applies computer vision algorithms and machine learning tools to calculate increased bilirubin levels. It does the task by analyzing the color information from the white portion of the eye, known as the sclera. A clinical study tested the app on 70 people and correctly identified 89.75 percent cases, showing even better results than the trials conducted using blood tests for jaundice detection.
You can perform a jaundice test using the app along with two accessories that dismiss the effects of varying light conditions. Paper glasses printed with colored squares that help the app to calibrate color according to light conditions and a 3D-printed box that blocks ambient lighting. The app not only helps in diagnosis but also eases the process of tracking the effects of the treatment.
Dr. Jim Taylor, the co-author of the research and a professor at UW Medicine Department of Pediatrics, explained,
“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.”
The research has started to work on an algorithm to diagnose Pancreatic cancer in its early stages, but the same can be applied to diagnose other conditions like Osteogenesis imperfecta, a genetic bone condition that produces a slight blue tinge in the sclera. Other ailments like Diabetes, Hyperemia, and Conjunctivitis also affect the coloration of the eye. Hence, such diseases can be diagnosed by tweaking these algorithms as per the demand.
The team hopes to make the app more accessible to a wider network of people as well as remove the need for additional accessories to make its usage a tad niftier.