L2M- Machine learning based point-of-care device for rapid diagnosis of clinically relevant fungal pathogens

This project aims to develop and bring to market a point-of-care test (POCT) device driven by artificial intelligence to identify pathogenic yeast species from microscopy images collected from clinical samples (blood and urine). We will evaluate the efficacy of microfluidic devices to aid in the capture of microscopy images of different yeast species and their classification using machine learning models. Furthermore, we will survey end users (clinicians, hospital management, and diagnostic laboratory technicians) and incorporate their feedback into our design of our POCT device. This device will enable healthcare providers to diagnose invasive fungal infections quickly and accurately, leading to better patient outcomes. The expected benefit to the partner organization includes an enhanced reputation by assisting innovators to develop cutting-edge, medical diagnostic technologies.

Faculty Supervisor:

Daniel Charlebois

Student:

Partner:

Edmonton Unlimited

Discipline:

Life Sciences

Sector:

Professional, scientific and technical services; Public administration

University:

University of Alberta

Program: