乌鸦传媒

A brain-computer interface (BCI) surgically implanted in a 45-year-old man with amyotrophic lateral sclerosis (ALS) and severe dysarthria performed well enough to restore conversational communication quickly, data from the BrainGate2 trial showed.

On the first day of use -- 25 days after surgery -- the BCI had 99.6% accuracy with a 50-word vocabulary. On the second day, it achieved 90.2% accuracy using a vocabulary based on a 125,000-word dictionary, reported David Brandman, MD, PhD, of the University of California Davis, and co-authors in the

With continued data collection and training, the BCI sustained 97.5% accuracy over 8.4 months after implantation.

This paper demonstrates the most accurate speech neuroprosthesis ever reported, Brandman said in a statement. "Previous speech BCI systems had frequent word errors. This made it difficult for the user to be understood consistently and was a barrier to communication," he noted. "Our objective was to develop a system that empowered someone to be understood whenever they wanted to speak."

The study involved four microelectrode arrays placed into the patient's left ventral precentral gyrus. The arrays recorded cortical neural activity from 256 cortical electrodes, which detected the patient's attempt to move his muscles to talk. Decoded words were shown on a screen and read aloud in a voice designed to sound like the patient before ALS.

The patient used it to communicate at a rate of approximately 32 words per minute for more than 248 cumulative hours, Brandman and co-authors reported.

The paper was one of two BCI studies published in the New England Journal of Medicine this week. The other, a by Mariska Vansteensel, PhD, of the University Medical Center Utrecht in the Netherlands, and colleagues, outlined 7-year outcomes of a 58-year-old woman with advanced ALS who had a BCI implanted as part of the Utrecht NeuroProsthesis (UNP) trial.

The was designed to help locked-in patients like her communicate at home.

In 2015, the researchers that included subdural electrodes positioned over the patient's motor cortex and a transmitter placed subcutaneously in her thorax. The implant, combined with decoding software, allowed her to interact with others.

For more than 3 years, the BCI was the patient's sole means of communication and the only way she could attract her caregiver's attention. The frequency of her at-home BCI use increased over time to compensate for her gradual loss of control of an eye-gaze tracking device. This was followed by a progressive decrease in BCI use starting 6 years after surgery.

Toward the end of the study, the BCI performance declined, and at-home use ended in 2023. No evidence of technical malfunction was seen.

CT scans showed the patient had progressive atrophy. This may have made it more difficult for her to reliably produce neural signal changes, suggesting that "ALS-related neurodegeneration ultimately rendered the brain-computer interface ineffective after years of successful use, although alternative explanations are plausible," Vansteensel and co-authors wrote.

"This study raises questions about the long-term performance of brain-computer interfaces in patients who have progressive neurodegenerative conditions such as ALS," observed Edward Chang, MD, of the University of California San Francisco, in a .

"Future efforts may need to interface with different brain regions that may be less affected (or less prone to degeneration during disease progression), but the activity from such regions may be harder to decode," he pointed out.

Both studies reported in this edition of the New England Journal "provide compelling new evidence of rapid progress in clinically viable, practical applications of brain-computer interfaces to restore communication to persons living with paralysis," Chang added.

"Both groups used older-generation research-grade neural interfaces with limitations in terms of electrode counts and long-term biostability," he noted. "But these and other studies have made it clear that persons with paralysis can meaningfully benefit from communication brain-computer interfaces, and it is clear that the development of newer devices and neural interfaces is critically needed."