WASHINGTON: during world first, US researchers have developed a neuroprosthetic device that successfully translated the brain waves of a paralyzed man into complete sentences, consistent with a scientific paper published Thursday.
“This is a crucial technological milestone for an individual who cannot communicate naturally,” said David Moses, a postdoctoral engineer at the University of California San Francisco (UCSF), and one among the lead authors of the study within the New England Journal of Drugs.
“It demonstrates the potential for this approach to offer a voice to people with severe paralysis and speech loss.”
The breakthrough involved a 36-year-old man who had a stroke when he was 20 that left him with anarthria — the lack to talk intelligibly, though his cognitive function had remained intact.
Every year, thousands of individuals lose the power to speak thanks to strokes, accidents, or disease.
Past research during this area has focused on reading brain waves via electrodes to develop mobility prosthetics that allow users to spell out letters.
The new approach was intended to enable more rapid and organic communication.
UCSF researchers had previously placed electrode arrays on patients with normal speech who were undergoing an operation, to decode the signals that control the vocal tract so as to precise vowels and consonants, and were ready to analyze the patterns to predict words.
But the concept hadn´t been tried out on a paralyzed patient to prove it could offer clinical benefit.
– ´Feat of neuro engineerings –
The team decided to launch a replacement study called Brain-Computer Interface Restoration of Arm and Voice, and therefore the first participant asked to be mentioned as BRAVO1.
Since suffering a devastating brainstem stroke, BRAVO1 has had an extremely limited head, neck, and limb movements, and communicates by employing a pointer attached to a jockey cap to poke letters on a screen.
The researchers worked with BRAVO1 to develop a 50-word vocabulary with words essential to his lifestyle like “water,” “family,” and “good,” then surgically implanted a high-density electrode over his speech motor area.
Over subsequent several months, the team recorded his neural activity as he attempted to mention the 50 words, and used AI to differentiate subtle patterns within the data and tie them to words.
To test it had worked, they presented him with sentences constructed from the vocabulary set and recorded the results on a screen.
They then prompted him with questions like “How are you today?” and “Would you wish some water?” which he was ready to answer with responses like, “I am excellent,” and “No, I’m not thirsty.”
The system decoded up to 18 words per minute with a median accuracy of 75 percent. An “auto-correct” function, almost like that utilized in phones, contributed to its success.
“To our knowledge, this is often the primary successful demonstration of direct decoding of full words from the brain activity of somebody who is paralyzed and can’t speak,” said BRAVO1´s neurosurgeon Edward Chang, a co-author.
An accompanying editorial within the journal hailed the event as “a feat of neuro engineering,” and suggested advancements in technology like smaller surface electrodes might help improve accuracy even further.