For the first time, a man paralysed from the neck down has been able to ‘handwrite’ by using a special AI brain chip.
The man, a 65-year old who had suffered a spinal injury, had two tiny electrodes put on the area of his brain associated with movement of his arm, and the sensors picked up activity as he thought about the hand movements needed to write certain letters, according to a study published today in Nature.
A machine learning algorithm then learned to recognise the brain patterns needed for each individual letter and ‘wrote’ out what he was thinking at about 18 words per minute – similar to the speed of somebody in their 60’s typing on a smart phone.
“We want to find new ways of letting people communicate faster,” says Frank Willett of Stanford University, who led the study. “This new system uses both the rich neural activity recorded by intracortical electrodes and the power of language models that, when applied to the neurally decoded letters, can create rapid and accurate text.”
The system was so quick because thinking about each letter has a unique and distinct brain activity pattern, so the algorithm was easily able to identify to letter needed. This could be useful for people who suffer paralysis, the authors say.
“An important mission of our BrainGate consortium research is to restore rapid, intuitive communication for people with severe speech or motor impairments,” says study director Leigh Hochberg of Brown University.
“[Willett’s] demonstration of fast, accurate neural decoding of handwriting marks an exciting new chapter in the development of clinically useful neurotechnologies.”