An Azure Hosted POC Application for Pallor Screening

Paul Hage1, Sohini Roychowdhury

  • 1MIPS Labs University of Washington Bothell

Details

09:05 - 09:55 | Fri 17 Feb | Ballroom D | FrRAF.24

Session: Rapid Fire Session 03: Sensor Informatics II

Abstract

Increasing costs of diagnostic healthcare have necessitated the development of hardware independent non-invasive Point of Care (POC) testing systems. In this work, we analyze a cloud-based platform hosted POC application, which is directed towards smart monitoring of anemia-like pallor. Although anemia prevalence rates in global populations vary between 10-60% in various demographic groups, smart monitoring systems have not yet been developed for screening and tracking the treatment of patients for anemia. Our POC diagnostic application focuses on detecting the presence of anemia through pallor site images of the tongue and eyes. The application consists of a front-end which is hosted on the Microsoft Azure cloud computing platform, and a back-end image processing algorithm. The front-end consists of a graphical user interface (GUI), designed to guide patients to upload images of their eye and tongue pallor site regions. From here, the back-end collects these images and performs a series of image processing techniques to assess and return the anemia-like pallor severity. Such a system provides affordable, accessible, and immediate results in a non-invasive manner. We observe low time-complexity of the cloud hosted front-end that is independent of the machine hosted back-end.