A groundbreaking new brain-computer interface (BCI) developed at UC Davis Health is changing the way people with speech impairments communicate. This innovative technology can translate brain signals into speech with up to 97% accuracy, making it the most accurate system of its kind. The BCI offers hope to individuals who have lost their ability to speak due to conditions like amyotrophic lateral sclerosis (ALS) or other neurological disorders.
Representational image.
How Does the New BCI Work?
The researchers at UC Davis implanted tiny sensors in the brain of Casey Harrell, a 45-year-old man with ALS. ALS, also known as Lou Gehrig’s disease, affects the nerve cells controlling muscle movements throughout the body. As the disease progresses, it can cause loss of control over muscles, including those needed for speech. This leads to difficulties in speaking and communicating.
The BCI works by interpreting the brain signals that are sent when the user tries to speak. These signals are then converted into text, which is read aloud by a computer. For people who cannot speak due to paralysis or neurological conditions, this technology offers a new way to communicate their thoughts and needs.
“Our BCI technology helped a man with paralysis to communicate with friends, family, and caregivers,” said Dr. David Brandman, a UC Davis neurosurgeon and co-senior author of the study. “Our paper demonstrates the most accurate speech neuroprosthesis ever reported.”
Breaking the Communication Barrier
The BCI system allows users to communicate in real time. When someone attempts to speak, the device captures their brain activity and transforms it into text that appears on a computer screen. The computer then reads the text out loud, replicating the user’s intended speech.
To develop this system, the team enrolled Harrell in the BrainGate clinical trial. At the time, Harrell had significant weakness in his arms and legs (tetraparesis) and difficulty speaking (dysarthria), requiring others to help interpret his speech.
In July 2023, Dr. Brandman implanted the BCI device in Harrell’s brain, placing four microelectrode arrays into the left precentral gyrus, a brain region responsible for coordinating speech. These arrays are designed to record brain activity from 256 cortical electrodes.
Casey Harrell with his personal assistant Emma Alaimo and UC Davis neuroscientist Sergey Stavisky. Credit: UC Regents
“We’re detecting their attempt to move their muscles and talk,” explained neuroscientist Dr. Sergey Stavisky, co-director of the UC Davis Neuroprosthetics Lab. “We are recording from the part of the brain that’s trying to send commands to the muscles. And we are translating those patterns of brain activity into phonemes — like syllables or units of speech — and then the words they’re trying to say.”
Faster Training, Better Results
Traditional speech BCI systems have faced challenges due to slow communication and high error rates. However, the new system developed at UC Davis has shown remarkable improvements. The BCI system can be trained quickly and provides high accuracy in real time, allowing for both prompted and spontaneous conversations.
During the first speech data training session, the BCI system took only 30 minutes to achieve a 99.6% word accuracy with a 50-word vocabulary. As the system continued to learn, the vocabulary expanded to 125,000 words. After just 1.4 hours of additional training data, the system achieved a 90.2% accuracy with the expanded vocabulary. Eventually, the system reached a remarkable 97.5% accuracy.
“At this point, we can decode what Casey is trying to say correctly about 97% of the time,” said Dr. Brandman. “This technology is transformative because it provides hope for people who want to speak but can’t. I hope that technology like this speech BCI will help future patients speak with their family and friends.”
Real-Life Impact of the BCI
Over 32 weeks, the researchers collected data from 84 sessions with Harrell. He used the BCI for over 248 hours, communicating both in person and via video chat. The system was able to maintain high accuracy and allow for smooth, real-time conversation.
The BCI system not only helps people regain their ability to speak but also restores their sense of independence. “Not being able to communicate is so frustrating and demoralizing. It is like you are trapped,” Harrell said. “Something like this technology will help people back into life and society.”
“It has been immensely rewarding to see Casey regain his ability to speak with his family and friends through this technology,” said Nicholas Card, the study’s lead author and a postdoctoral scholar in the UC Davis Department of Neurological Surgery.
A Step Towards the Future of Communication
This innovative technology is a significant advancement in the field of neuroprosthetics and offers a promising solution for many people who have lost their ability to speak. “Casey and our other BrainGate participants are truly extraordinary,” said Dr. Leigh Hochberg, co-author and BrainGate trial sponsor-investigator. “They deserve tremendous credit for joining these early clinical trials. They do this not because they’re hoping to gain any personal benefit, but to help us develop a system that will restore communication and mobility for other people with paralysis.”
The BrainGate2 clinical trial, which is still enrolling participants, is paving the way for future advancements in BCI technology. For more information about the study, visit braingate.org or contact braingate@ucdavis.edu.
Conclusion
The new brain-computer interface technology developed by UC Davis Health marks a breakthrough in restoring speech for people with neurological conditions like ALS. With its high accuracy and real-time communication capabilities, this innovative device brings new hope and independence to those who have lost their ability to speak. As research and development continue, this technology could become a vital tool in improving the quality of life for countless individuals worldwide.
A study about this work was published in the New England Journal of Medicine.
Source : Eurekalert , Interesting Engineering