Brain waves of a paralyzed man turned into speech in the first global hack

[ad_1]

For the first time in the world, US researchers have developed a compensatory nervous system that successfully translates the brain waves of a paralyzed man into complete sentences, according to a scientific paper published Thursday.

“This is an important technology milestone for someone who can’t communicate normally,” said David Moses, a postdoctoral engineer at the University of California San Francisco (UCSF), and one of the study’s lead authors in the New England Journal of Medicine. .

“It demonstrates the ability of this approach to give voice to people with severe paralysis and aphasia.”

This breakthrough involved a 36-year-old man who had had a stroke when he was 20, which left him with anarthrosis – the inability to speak clearly, even though his cognitive function remained intact.

Every year thousands of people lose the ability to speak due to stroke, accident or disease.

Previous research in this area has focused on reading brain waves through electrodes to develop motor prosthetics that allow users to spell letters.

The aim of the new approach was to enable an organic and rapid connection.

UCSF researchers previously placed electrode arrays on patients with normal speech undergoing brain surgery, to decode the signals that control the vocal tract in order to express vowels and consonants, and were able to analyze the patterns to predict words .

But this concept has not been tested on a paralyzed patient to show that it can provide clinical benefit.

Neuroengineering work

The team decided to launch a new study called Brain-Computer Interface Restoration of Arm and Voice, and the first participant asked to be referred to as BRAVO1.

Since suffering a devastating stroke, BRAVO1 has had very limited movements of the head, neck, and extremities, and communicates using a pointer attached to a baseball cap to poke characters on the screen.

The researchers worked with BRAVO1 to develop a 50-word vocabulary with basic everyday words such as “water,” “family,” and “good,” and then surgically implanted a high-density electrode over the motor cortex of speech.

Over the next few months, the team recorded its neural activity as it attempted to pronounce the 50 words, and used artificial intelligence to discern subtle patterns in the data and associate them with the words.

To test his success, they gave him sentences made up of the vocabulary set, and recorded the results on a screen.

Then they asked him questions like, “How are you today?” and “Would you like some water?” Which he was able to answer with responses like “I’m very good” and “No, I’m not thirsty.”

The system decoded up to 18 words per minute with an average accuracy of 75 percent. Its “auto-correction” function, similar to that used in phones, contributed to its success.

“To our knowledge, this is the first successful demonstration of a direct decoding of whole words from the brain activity of a person who is paralyzed and unable to speak,” said Edward Chang, a neurosurgeon at Bravo1.

An accompanying editorial in the journal praised the development as a “feat of neural engineering,” and suggested advances in technology such as smaller surface electrodes might help improve accuracy even further.

© AFP

.

[ad_2]