Brain-Computer Interface Turns Thoughts to Text

Breakthrough tech defines "a new kind of writing," researchers say.

By Hope Reese
Jan 6, 2022 6:00 AMJan 6, 2022 2:24 PM
BCI illo
(Credit: Eamesbot/Shutterstock)

Newsletter

Sign up for our email newsletter for the latest science news
 

This story was originally published in our January/February 2022 issue. Click here to subscribe to read more stories like this one.


A major advancement in the field of brain-computer interface (BCI), announced in May, allowed a paralyzed man to imagine writing and have the words translated to text.

Researchers used an experimental device to tap into surgically implanted electrodes, capturing activity in the region of the brain responsible for physical movement. When the quadriplegic patient envisioned writing individual characters by hand, words flew across the screen. The text was highly accurate (95 percent) and arrived faster (90 characters per minute) than any other BCI, coming in at around the same speed performed by similarly aged people typing on their smartphones.

Led by Frank Willett, a research scientist with the Braingate research consortium, the new system doubles the speed of previous thought-to-text BCI tools, which had subjects look at a screen and mentally “point and click” — as if using a cursor — rather than simply imagining writing the letter. 

Gernot Müller-Putz, the head of the Institute of Neural Engineering at Graz University of Technology in Austria, says that the current research is “really advancing the field.” Müller-Putz has researched BCI for decades, developing prosthetic tools for people with spinal cord injuries.

In the late 1960s, BCI research was first conducted on monkeys; human trials began in the early 2000s. The current research involves placing tiny electric arrays (a matrix of electrodes) directly into the motor cortex of the subject, which records neuron activity. Working with tech that previously controlled the movement of robotic arms (albeit slowly), researchers were able to use very quick, tiny movements, separated from each other, to create a spelling device.

A computer was programmed to recognize brain activity that corresponded with the alphabet. So when a subject imagines an A, the device knows exactly how to interpret those electrical signals in order to produce the correct letter on the screen. “They defined a new kind of writing,” Müller-Putz says. When the paralyzed person imagined and attempted writing each letter, specific, separate signals were also captured in the motor area.

The new device may be of great use to stroke victims who cannot move or speak, allowing them to message via email or other online platforms for personal and professional communication. It could help those with neurodegenerative diseases, as well.

1 free article left
Want More? Get unlimited access for as low as $1.99/month

Already a subscriber?

Register or Log In

1 free articleSubscribe
Discover Magazine Logo
Want more?

Keep reading for as low as $1.99!

Subscribe

Already a subscriber?

Register or Log In

More From Discover
Recommendations From Our Store
Shop Now
Stay Curious
Join
Our List

Sign up for our weekly science updates.

 
Subscribe
To The Magazine

Save up to 40% off the cover price when you subscribe to Discover magazine.

Copyright © 2024 Kalmbach Media Co.