Neuroprosthesis Enables Paralyzed Man to Communicate in Sentences

A man with severe paralysis is now able to communicate in full sentences thanks to a new speech neuroprosthesis device developed by researchers at UC San Francisco.

“To our knowledge, this is the first successful demonstration of direct decoding of full words from the brain activity of someone who is paralyzed and cannot speak,” said Edward Chang, lead author on the study and the Joan and Sanford Will Chair of Neurological Surgery at UC San Francisco.

The breakthrough study, which was published in the New England Journal of Medicine, comes after more than a decade of effort by Chang to develop a device capable of returning speech to paralyzed individuals who cannot speak on their own.

Previous works in communication neuroprosthesis attempted to allow for speech through approaches involving the typing out of words into text. These methods were slow and tedious, requiring patients to pick out individual letters from an on-screen keyboard. Communicating entire sentences with these methods is difficult and time consuming.

Chang’s study allows for paralyzed individuals to communicate in a manner that’s faster, more organic, and fluid than ever before. Instead of tapping into neurosignals sent to the arm or hand to maneuver a cursor on a screen, the new device translates signals intended for the vocal muscles into full words and sentences.

In the study, Chang notes that spelling-based approaches are laborious and slow: “With speech, we normally communicate information at a very high rate, up to 150 or 200 words per minute. Going straight to words, as we’re doing here, has great advantages because it’s closer to how we normally speak.”

Chang’s team implanted an electrode array over the patient’s speech motor cortex. Using custom neural networks, the researchers taught an artificial intelligence model to identify brain activity patterns associated with the patient’s attempts to speak.

The researchers say that their novel neuroprosthesis is capable of decoding up to 18 words per minute with a maximum accuracy of 93 percent. David Moses, a postdoctoral engineer at Change’s lab, is thrilled with the results: “We’ve shown that it is actually possible to facilitate communication in this way and that it has potential for use in conversational settings.”

The researchers plan to conduct an expanded trial of the device on more participants.

Another Interesting Reading: The U.S. on Track to 70 Percent Vaccination Rate against COVID-19 by Summer

You May Also Like

About the Author: Webby Feed Staff

Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.