🧠 Paralyzed man can speak with the help of a "neuroprosthesis"

🧠 Paralyzed man can speak with the help of a "neuroprosthesis"

Electrodes in the brain can detect brain activity and link the activity to the specific words that a patient wants to say.

Kent Olofsson
Kent Olofsson

Share this story!

A paralyzed man who has lost the ability to speak can now communicate using a "neuroprosthesis." This is what researchers at the University of California San Francisco call their new technology for converting signals from the brain into text on a screen.

The researchers inserted electrodes into the area of ​​the brain that normally controls our speech. Then the patient was allowed to see simple everyday questions on a screen and was asked to give a certain answer. An algorithm learned to recognize 50 words that it can combine into over 1,000 sentences.

According to the researchers, this is the first time that brain activity has been able to be converted into complete words. The technology is not perfect yet, but on average, the algorithm is right 78 percent of the time and can handle 15 words per minute. At best, the algorithm is right 93 percent of the time and manages 18 words per minute, so the researchers hope to be able to make the method more accurate in the future.


The patient previously used a kind of stick attached to a hat to use the stick to point at a screen. In this manner, he could write words letter by letter. By being able to write whole words by just thinking about them, communication is a lot faster.

So far, the method has only been tested on one patient, and there is a lot of work left before it can become a clinical treatment. But the researchers have high hopes of being able to develop the method so that it can work for many different types of injuries and understand more words and more quickly.

"This is an important technological milestone for a person who cannot communicate naturally. And it demonstrates the potential for this approach to give a voice to people with severe paralysis and speech loss.”, says David Moses, one of the researchers behind the method, in a press release.

Photo: University of California San Francisco