New, high-performance brain-computer interfaces (BCIs) helped restore speech to individuals who had lost the ability, including a paralyzed patient, according to two new studies published separately in Nature.
In the BrainGate2 study, researchers used a speech-to-text BCI that used activity from four intracortical microelectrode arrays to decode the speech of a patient with amyotrophic lateral sclerosis.
Pat Bennett, the 68-year-old patient, had tiny sensors implanted into her brain in an area that is involved with speech. The sensors connected to wires that carried signals from her brain to a computer. The computer was trained to decode Bennett's brain activity when she attempted to make specific phonemes, or speech sounds, which were then processed by a language model.
"The language model is essentially a sophisticated auto-correct," said Jaimie Henderson, a professor of neurosurgery at Stanford University whose lab created the system Bennett used. "It takes all of those phonemes, which have been turned into words, and then decides which of those words are the most appropriate ones in context."
The system was able to decode Bennett's speech at a rate of 62 words per minute, which was over three times faster than the last record. Overall, she was able to communicate with a 9.1%-word error rate using a 50-word vocabulary and a 23.8%-word error rate using a 125,000-word vocabulary.
"She's able to do a very good job with it over short stretches," Henderson said. "But eventually there are errors that creep in."
In a separate study called BRAVO, researchers placed a silicon sheet with 253 electrocorticography electrodes onto the surface of the brain of a patient who have suffered a brainstem stroke. The electrodes recorded signals to muscles in the tongue, jaw, larynx, and face.
This study builds on previous research from the same team. In 2021, researchers reported that the approach allowed a man who had had a stroke to speak through text on a computer screen.
In this new study, an improved version of the system was implanted into Ann Johnson, a 48-year-old who had suffered a stroke when she was 30. The system was trained on a 1,024-word vocabulary and could decode and create sentences with a 25.5%-word error rate. On a 50-phrase set, the word error rate was 4.9%.
In addition to deciphering sentences, the BCI also attempted to decode facial expressions, which were shown on a digital avatar. The system used signals as Johnson tried to speak to make the avatar's jaw, lips, and tongue move. The avatar also expressed happiness, sadness, or surprise through its facial movements.
"Our goal is to restore a full, embodied way of communicating, which is really the most natural way for us to talk with others," said Edward Chang, a neurosurgeon at the University of California, San Francisco who led the BRAVO team. "These advancements bring us much closer to making this a real solution for patients."
In an editorial accompanying the two studies, Nick Ramsay, a cognitive neuroscientist at the Utrecht Brain Center, and Nathan Crone, a professor of neurology at Johns Hopkins University, said that "these systems show great promise in boosting the quality of life of individuals who have lost their voice as a result of paralyzing neurological injuries and diseases."
Similarly, Henderson said the results are "an encouraging proof of concept" and that he's "confident that within 5 or 10 years we'll see these systems actually showing up in people's homes." Currently, the systems can only be used in a lab and require wires, but researchers are working on wireless, consumer-friendly versions.
Separately, Chang said additional features, such as a digital avatar with facial expressions, made the BCI system more engaging for patients.
"Hearing someone's voice and then seeing someone's face actually move when they speak, those are the things we gain from talking in person, as opposed to just texting," he said. In addition, "[t]here is this aspect to it that is, to some degree, restoring identity and personhood."
So far, the patients who have tested the BCI systems have spoken positively about the progress they've been able to make with them. "It let me feel like I was a whole person again," Johnson said. (Belluck, New York Times, 8/23; George, MedPage Today, 8/23; Hamilton, "Shots," NPR, 8/23)
Create your free account to access 1 resource, including the latest research and webinars.
You have 1 free members-only resource remaining this month.
1 free members-only resources remaining
1 free members-only resources remaining
Never miss out on the latest innovative health care content tailored to you.