BiliScreen uses a smartphone camera, computer vision algorithms and machine learning tools.
A team of researchers at the University of Washingtonhas developed a mechanism called BiliScreen that relies on analysis of a selfie the patient snaps in order to detect pancreatic cancer by looking for traces of jaundice.
According to a report from Washington.edu, “BiliScreen uses a smartphone camera, computer vision algorithms and machine learning tools to detect increased bilirubin levels in a person’s sclera, or the white part of the eye. The app is described in a paper to be presented Sept. 13 at Ubicomp 2017, the Association for Computing Machinery’s International Joint Conference on Pervasive and Ubiquitous Computing.”
Pancreatic cancer has a fairly low survival rate compared to other cancers because there are no easy access screening tools. Most patients only learn of the diagnosis after seeking medical treatment for advanced symptoms, which indicates the cancer has basically gone too far. Even in patients who receive “successful” treatment, the five-year life expectancy is only nine percent.
Future is already here
This juxtaposition of readily available technology and medical science might seem very “wave of the future,” but the popularity of video chat doctors’ appointments through apps like Doctor on Demand show that tech consumers and researchers alike are already aware of the benefits that a quick peek with a smartphone camera can provide. It’s not hard to envision doctors relying on BiliScreen for early detection as part of a routine physical due to its non-invasive and affordable functionality.
Not just AI
Proving that humans can still cut it in the dianosis game, registered nurse Ryan Reid made headlines in 2013 for a fairly unusual diagnosis. While binge watching a Flip or Flop marathon on popular home improvement network HGTV, she noticed that one of the show’s hosts had an unusual lump at the base of his throat. She felt compelled to contact the show’s producers about the issue, and the host was diagnosed with a malignant tumor on his thyroid; the cancer had spread to his lymph nodes, but the spread was minimal thanks to his early detection. Reid was hailed as a hero not just for reaching out to the network, but for even being able to detect something so minute from a recorded broadcast.