By A man who lost the ability to speak after suffering a massive brainstem stroke 15 years ago is finally learning how to communicate again. Scientists were able to install a special device into the man’s brain that translates his brain waves into words. It’s considered a groundbreaking achievement for the medical community. The device could be used to help thousands of paralyzed individuals communicate with their loved ones.
A New Way to Communicate
Edward Chang, a neurosurgeon at the University of California, San Francisco who led the study, says his team used speech neuroprosthesis to help a man in his late 30s, identified only as BRAVO1, communicate in full sentences. BRAVO stands for (Brain-Computer Interface Restoration of Arm and Voice). He previously used a pointer attached to a baseball cap to point to words on a screen when he wanted to share his thoughts. Now, the new device translates signals sent from the brain to the vocal track, while displaying them on a monitor.
“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,” Chang said in a statement. “It shows strong promise to restore communication by tapping into the brain’s natural speech machinery.”
UCSF released a video of the man using the neuroprosthesis. Researchers can be heard in the background. “How are you today?” they ask. The computer algorithm then translates the man’s brain waves into digital text.
“I am very good,” the man’s response read.
Chang added that the algorithm can be used to interpret 50 words in the English language, which can be used to form around 1,000 different sentences. The man’s speech is still limited, but this gives him the ability to share his thoughts on a range of issues. The man’s new vocabulary includes common words like “water,” “family,” and “good”.
The system works surprisingly fast, as well. “We decoded sentences from the participant’s cortical activity in real time at a median rate of 15.2 words a minute, with a median word error rate of 25.6%,” the researchers added.
However, there are still some kinks to work out. “In post hoc analyses, we detected 98% of the attempts by the participant to produce individual words and we classified words with 47.1% accuracy using cortical signals that were stable throughout the 81-week study period.”
The study analyzing the results, recently published in the New England Journal of Medicine, says it took about four seconds for the words to appear on the screen after the man tried to respond, which is a bit slower than normal speech but faster than having to type it out.
To create the device, scientists had to map out the cortical activity patterns associated with vocal track movements that produce certain vowels and consonants.
Lead author David Moses celebrated the news. “We were thrilled to see the accurate decoding of a variety of meaningful sentences. We’ve shown that it is actually possible to facilitate communication in this way and that it has potential for use in conversational settings.”
Moses was the one that helped create the system for decoding brain signals sent to the voice track. He also created a “auto-correct” function, similar to the ones we use when composing a text or email.
Chang added that the results are more effective when scientists interpret signals to the voice track as opposed to sending signals to the limbs that then have to select the words or letters from a screen.
“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,” he said.
A Fresh Start
The medical and scientific communities are praising the results. Two neurologists with Harvard University referred to the study as a “pioneering demonstration” in an op-ed in the New England Journal of Medicine, saying the device could be used to help those with amyotrophic lateral sclerosis, cerebral palsy, stroke, and other disorders that affect neurological functions.
“Ultimately, success will be marked by how readily our patients can share their thoughts with all of us,” Leigh Hochberg and Sydney Cash wrote in the piece.
The author of the study added that thousands of people lose the ability to speak due to stroke, accident, or disease every year, and this technology could bring them some much-needed hope and relief.
“This is an important technological milestone for a person who cannot communicate naturally,” said Moses, “and it demonstrates the potential for this approach to give a voice to people with severe paralysis and speech loss.”
