Affordable brainwave reader to support people with advanced MND

Professor Amin Al-Habaibeh, an expert in intelligent engineering systems, wanted to support charities which help people with advanced Motor Neurone Disease (MND) and Completely Locked-in Syndrome after his brother-in-law, Mr Naeem Radwan, passed away aged 38 after having MND.

The research has led to the development of a brainwave reader which is made affordable by using off-the-shelf parts and a novel artificial intelligence (AI) algorithm developed by the research team.

The technology centres on interpreting people’s brain signals when they are invited to envisage contrasting imaginary situations to indicate ‘yes’ or ‘no’ answers.

For example, patients can be asked to imagine the joy of kicking a football to indicate ‘yes’, but by contrast be asked to imagine being trapped in a room with an elephant to mean ‘no’.

The diverse imaginations, which produce different analogue signals in the brain, are detected over five seconds by three electroencephalogram (EEG) sensors attached to the patient’s head.

These analogue signals are then magnified and converted to digital signals before being interpreted by the AI and relayed to a display screen to show the answer.

“This technology can allow people who are in the late stages of MND to communicate critical information when they are unable to even blink,” said Professor Al-Habaibeh, of the School of Architecture, Design and the Built Environment.

“It could be used for a variety of purposes, such as to communicate what a patient’s wishes may be, whether they are comfortable, if they would like any further medication, and more.

“Our aim is to make this technology affordable for organisations such as charities so that it can be used more widely by families or hospices, rather than as a commercial venture.

“By allowing better communication in the later stages of MND, it will also allow medical professionals to treat patients better and take key decisions which are in line with the patient’s wishes.

“With further research, we are confident that this approach could allow a patient to control a cursor on a computer screen, potentially with just four imaginations for up, down, left and right.

“It may also be possible for this technology to be applied to mental health outputs, including detecting levels of stress.”

The research found that the technology takes around ten attempts to learn an individual’s brain signal pattern, and that the individual success rate is around 90 per cent if the patient is able to focus without any distraction.

The cost of hardware for each reader is estimated at around £300, and the research is being published under a creative commons licence to allow organisations to use it freely without copyright.

Research on the technology has previously been published by the Neuroscience Informatics journal and a working prototype has now been created as the culmination of the project.

Researcher Sharmila Majumdar, a PhD candidate who worked on the project, said: “This technology has the potential to help dying people communicate when they are in an incredibly vulnerable state.

“We are proud to have carried out this research to support those with MND and for it to published it freely in the interests of helping others.”

Project co-supervisor Dr Ahmet Omurtag, of NTU’s School of Science and Technology, said: “Existing medical EEG devices tend to be expensive, so I think the capability to decipher people's thoughts using only a few sensors will continue to increase in value and find more applications.”