Scientists develop mobile phone app to diagnose TB

Anne Gulland
A three-month old TB patient at Kerema General Hospital in Papua New Guinea - where the disease is rife - Tom Maguire/Results UK

A mobile phone app that can diagnosis tuberculosis in a matter of minutes could revolutionise treatment of the disease in some of the world's poorest countries.

Computer scientists at Anglia Ruskin University and Universiti Putra in Malaysia have developed a mobile phone testing system which has a 98 per cent accuracy rate in diagnosing the fatal lung disease.

Tuberculosis is the world’s leading infectious disease killer and the latest figures from the World Health Organization show there were 10 million cases of the disease in 2017 and 1.6m deaths. The majority of these are in low-income countries where health care workers have poor access to testing and treatment facilities.

The research team has come up with a system which enables doctors or other health workers to detect TB-specific antibodies in a patient’s sputum. The patient produces a sample of sputum - this is put onto a tiny biosensor device which produces a colour, depending on whether it is positive or negative for TB.

Via a smartphone's camera the app then analyses the colour and delivers a diagnosis within seconds.

Alamgir Hossain, director of the Anglia Ruskin IT Research Institute, said analysis of colour samples using the naked eye alone was notoriously difficult. 

“By using the phone’s camera to capture the sample, rather than manually using colour charts, it eliminates human error and avoids any subjectivity around interpretation.  It also means that positive and negative samples do not need to be distinguishable to the human eye or depend on perfect colour vision,” said Prof Hossain.

“This system wouldn’t be used instead of seeing a physician but would be a first port of call.  If the app detects tuberculosis it would instruct the user to contact a medical professional,” he added.

The scientists hope to eventually add in DNA sequencing to enable the diagnosis to be more robust, said Prof Hossain.

“If you add in the DNA sequencing on top of the biosensor the overall framework for the diagnosis will be much better and doctors will be able to consider this as a primary diagnosis. Many remote areas have limited testing facilities so if you can develop a mobile system it will really help,” he said.

As well as a smartphone the health worker needs to purchase a small biosensor which has been developed by Universiti Putra. No additional hardware is needed and the system works offline so can be used in areas without internet connection.

Prof Hossain believes that the final cost for the system - downloading the app and purchasing the biosensor - could be as little as £2 to £3, depending on funding and uptake.

The scientists hope that the diagnostic test, developed with a £129,000 grant from the Newton Fund, will be ready to launch in two years.

Prof Hossain is currently supervising three PhD students looking at the use of mobile apps to diagnose diseases such as diabetes and coronary heart disease.

“Mobile apps are a growing market in the UK and they have a lot of potential for diagnosing disease,” he said.

Protect yourself and your family by learning more about Global Health Security