A person living with severe paralysis from ALS has successfully used a brain-computer interface (BCI) at home for nearly two years, communicating more than 2 million words with 99% accuracy and without needing researcher support. The achievement, published in Nature Medicine, marks a major milestone in translating brain-computer technology from controlled lab settings into practical, real-world assistive devices.

What Makes This Brain-Computer Interface Different?

Casey Harrell, a 47-year-old man with ALS, participated in the BrainGate2 clinical trial conducted by UC Davis in collaboration with Brown University and Mass General Brigham Neuroscience Institute. In 2023, neurosurgeon David Brandman implanted four microelectrode arrays containing 256 cortical electrodes into Harrell's brain, specifically in the left precentral gyrus, a region responsible for coordinating speech.

The BCI system works by decoding neural signals linked to attempted speech and movement. Advanced algorithms translate these brain signals into text for communication and enable cursor control for computer navigation. Over nearly two years, Harrell used the system independently on a near-daily basis, accumulating more than 3,800 hours of use.

The results were striking. Harrell communicated more than 183,000 sentences and close to 2 million words, averaging 56 words per minute. He rated 92% of his sentences as accurate or mostly correct, while the system achieved over 99% word accuracy in controlled testing with a 125,000-word vocabulary.

How Does This Improve on Previous Brain-Computer Interface Technology?

Earlier BCI systems achieved high accuracy in research settings but faced two critical barriers: they required researcher support to operate, and their performance degraded over time in real-world conditions. This new system overcomes both challenges.

"For years, BCIs have been proof-of-concept devices that lived in highly controlled research labs. This work shows that we may have crossed a threshold, by empowering a person with paralysis to speak on his own terms," said David Brandman, neurosurgeon and co-director of the UC Davis Neuroprosthetics Lab.

David Brandman, Neurosurgeon and Co-Director, UC Davis Neuroprosthetics Lab

The previous generation of this technology achieved 97% accurate word decoding but required a researcher to set up the system each time. The new version improved accuracy to 99%, maintained stable performance for nearly two years, and allowed Harrell to operate it independently at home whenever he wanted.

"Casey can use the system to communicate his own thoughts, not only while we're there in a controlled environment, but whenever he wants. Sometimes, he would do that over 12 straight hours," said Nicholas Card, lead author and postdoctoral scholar in the UC Davis Department of Neurological Surgery.

Nicholas Card, Postdoctoral Scholar, UC Davis Department of Neurological Surgery

What Can Harrell Do With the Brain-Computer Interface?

The system enables full digital independence for someone with severe paralysis. By combining speech decoding for text input and cursor control for navigation, Harrell can perform tasks that most people take for granted:

• Communication: Send emails and messages, browse the internet, and maintain ongoing conversations with family and friends
• Employment: Operate his computer independently to support employment despite complete paralysis
• Personal Connection: Share memories and stories with loved ones, including explaining to his daughter what his voice sounded like before ALS affected his speech

"It is very sweet to have the ability to look at my wife's eyes when she hears my voice and conjures up a sweet memory and to explain to my daughter who does not really remember anything about when I was still talking to them and remind them of what I used to sound like," Harrell shared through the BCI system.

Casey Harrell, BrainGate2 Clinical Trial Participant

Why Does This Research Matter Beyond One Patient?

Harrell's nearly 3,800 hours of brain recordings represent the largest individual brain recording dataset with single-neuron resolution ever collected, according to researchers. This wealth of data is helping scientists better understand how the human brain produces speech, which could lead to even more effective therapies in the future.

"In addition to testing a way to restore communication, this clinical trial is producing a wealth of unique data that we're studying to better understand how the human brain produces speech. As far as we know, these 3,800 hours of brain recording as Casey used the system is by far the largest individual brain recording dataset with single neuron resolution. This will help us develop even better therapies," explained Sergey Stavisky, neuroscientist and co-director of the UC Davis Neuroprosthetics Lab.

Sergey Stavisky, Neuroscientist and Co-Director, UC Davis Neuroprosthetics Lab

The findings highlight the potential of intracortical BCIs as transformative assistive tools for individuals with severe motor impairments, including ALS, spinal cord injuries, and other neurological conditions. By enabling naturalistic communication and full digital access, such systems may significantly improve independence and quality of life for people who would otherwise have no way to interact with the world.

The BrainGate2 clinical trial is still enrolling participants. Researchers emphasize that this fundamental advance in BCI technology would not have been possible without the dedication of trial participants willing to work with scientists to push the boundaries of what's possible in brain-computer interfaces.