Neural interface allowed paralysed man to respond to questions at same rate as someone typing on a smartphone
In a world first, scientists have developed a brain-computer interface that can instantly turn mental handwriting into text on a screen.
The system, developed by the BrainGate consortium, involves an implanted sensor that records the brain signals associated with handwriting, before translating them to a computer in real time at a rate of 90 characters per minute.
“An important mission of our BrainGate consortium research is to restore rapid, intuitive communication for people with severe speech or motor impairments,” said Dr Leigh Hochberg, who directed a clinical trial of the technology.
“[The] demonstration of fast, accurate neural decoding of handwriting marks an exciting new chapter in the development of clinically useful neural technologies.”
The previous record of thought-to-text translation was 40 characters per minute, which used a different approach of having a participant think about the motions involved in pointing to and clicking letters on a virtual keyboard.
The research, published in the journal Nature on Wednesday, could help people with severe disabilities communicate fluently using only their thoughts.
The trial of the new method allowed the 65-year-old participant, who was paralysed from the neck down, who volunteered to have two tiny electrodes the size of a baby aspirin in a part of his brain that controls the movement of his right arm and hand.
This system allowed him to respond to questions at a rate similar to someone typing on a smartphone.
“The people who enroll in the BrainGate trial are amazing,” Dr Hochberg said.
“It’s their pioneering spirit that not only allow us to gain new insights into human brain function, but that leads to the creation of systems that will help other people with paralysis.”