Stellenbosch University develops mobile app to detect TB cough
This innovation could revolutionise TB diagnosis, ensuring faster, more efficient testing of more people.
FILE: A digitally colourised scanning electron microscopic image depicts a grouping of red-coloured, rod-shaped Mycobacterium tuberculosis bacteria which cause tuberculosis in human beings. Picture: National Institute of Allergy and Infectious Diseases
Amy Maclver speaks to Prof. Grant Theron, Biomedical Sciences and Human Genetics researcher at Stellenbosch University. He shares more on this project and its potential impact on global health.
Listen to the interview in the audio below.
Stellenbosch University researchers, joined by an international team, are developing a mobile app that will be able to detect a cough particular to tuberculosis (TB).
The diverse research team crucial to the success of the project, comprises more than 30 experts from Stellenbosch University, the Amsterdam Institute for Global Health and Development, Uganda's Makerere University, and Germany's University of Göttingen.
According to Theron, the innovative tool will be able to fast-track TB diagnosis by detecting patients who need further examination.
He said the mobile CAGE-TB app and cough detector will be able to conduct tests without collecting a specimen.
The affordable app will focus on serving low-income communities, Theron added.
“The CAGE-TB app represents a tremendously exciting opportunity to transform TB diagnosis at scale, ensuring more people are tested, testing itself is done more efficiently, and TB is diagnosed earlier, stopping transmission in its tracks. Most people with TB may... not yet have symptoms, so we want to catch people before they get sick, because that's how we stop transmission."
- Prof. Grant Theron, Stellenbosch University
The CAGE-TB app will make use of algorithms that can distinguish between TB- and non-TB-related coughs. These algorithms are based on soundbites of coughs collected from trial participants.
It's also reported that the app aims to systematically identify people who need costly, yet essential, testing. This will transform the process in which potential TB patients are managed upon clinic entry.
How will the app work?
According to reports, the research is being conducted in two phases: discovery and validation.
In the discovery phase, data will be collected from a cohort in Cape Town to refine the cough audio signal specific to TB.
This involves advanced machine-learning methods tailored for audio analysis of a TB patient's cough.
The validation phase will use the optimized TB audio signature from the discovery cohort to validate the technology across broader populations in Cape Town and Uganda's capital Kampala, a statement said.
How far is the app?
The project is about two-thirds of the way in distinguishing the sound of a TB cough from other types of coughing.
“Currently, we have operational systems running on large computers in the laboratory. The journey involves updating these systems with more data, which is actively being collected to enhance reliability. We will then need to port the laboratory system into a smartphone device," explains the statement.
A proof-of-concept and a prototype has already been developed and successfully tested in a small-scale laboratory environment.
Next steps...
The prototype will be refined with additional data and adequate features, and repeatedly tested for increased performance.
The first revealing analysis will take place when the revised prototype is integrated into the mobile app, and a larger scale field experiment has been conducted, said the statement.
Read the full statement about this revolutionising technology here.
Scroll up to listen to the full conversation.