UK scientists have developed a mobile phone app that uses artificial intelligence to detect tuberculosis (TB).
The infectious lung disease is one of the top 10 causes of death worldwide, killing over one million people every year.
Details of the intelligent mobile-enabled expert system, which was developed by a team led by scientists from Anglia Ruskin University, have been published in the journal Expert Systems with Applications.
The app uses a regular smartphone camera to digitally capture a ‘biosensor’ with a sputum sample – a mixture of saliva and mucus coughed up from the respiratory tract – and then uses artificial intelligence (AI) to analyse the images and automatically detect TB-specific antibodies. Results are provided to users within a couple of seconds.
By using the phone’s camera, rather than manual colour charts, it eliminates human error and avoids any subjectivity around interpretation, said Professor Alamgir Hossain of Anglia Ruskin University, a co-author of the research paper. It also means that positive and negative samples do not need to be distinguishable to the human eye or depend on perfect colour vision.
According to the developers, the new system has a 98.4% accuracy rate in detecting TB antigen-specific antibodies.
The high rate of mobile phone use in developing countries means that it can reach a wide population, particularly benefiting those who have limited access to advanced laboratory facilities, Anglia Ruskin University said.
What’s more, because the system works offline, it can be used even in very remote areas.
“This system wouldn’t be used instead of seeing a physician but would be a first port of call,” Professor Hossain explained. “If the app detects tuberculosis it would instruct the user to contact a medical professional.”
The developers hope the app will be in use within the next two years.