Peer-reviewed research
Long-term independent use of an intracortical brain-computer interface for speech and cursor control
Nicholas S. Card et al., Nature Medicine, 2026 · DOI 10.1038/s41591-026-04414-6
Read the originalRead on October 17, 2026
- What it is
- A BrainGate study of one man with ALS who used an intracortical speech and cursor implant at home for almost two years, with no researchers present. The abstract reports his average communication rate, the share of sentences he rated as correct, and a comparison of silent and vocalized speaking in a copy task.
- How much weight it carries
- Peer-reviewed in a major journal, with unusually long real-world data. It is still a single participant, the system was updated during the study, and the words-per-minute figure is an average over real use, not a controlled test. Treat it as evidence of what one person achieved, not of what most people with paralysis will achieve.
Facts taken from this source
- In the 2026 Nature Medicine study, the participant used the brain-computer interface at home for more than 3,800 hours with no researchers present.
“the participant used the BCI for more than 3,800 h at home with no researchers present” (Abstract)
- In the 2026 Nature Medicine study, the participant labeled 92 percent of his sentences as decoded at least mostly correctly.
“He labeled 92% of sentences as being decoded at least mostly correctly” (Abstract)
- In the 2026 Nature Medicine study, the participant communicated with the speech BCI at home at an average rate of 56 words per minute over almost two years of use.
“at an average rate of 56 words per minute” (Abstract)
- The 2026 Nature Medicine study of a speech and cursor brain-computer interface reports results from one participant, a man with paralysis and severe dysarthria due to ALS.
“decoders by a man with paralysis and severe dysarthria due to amyotrophic lateral sclerosis” (Abstract)
- In a 2026 copy task, the participant's silent speech was decoded at an average of 49.7 words per minute, with accuracy of 96.5 percent.
“with silent speech, accuracy reached 96.5% at 49.7 WPM average” (Results, copy task comparing silent and vocalized speech)
- In the same 2026 copy task, the participant's vocalized speech was decoded at an average of 30.6 words per minute, with accuracy above 99 percent.
“During vocalized speech, accuracy exceeded 99% at 30.6 WPM average” (Results, copy task comparing silent and vocalized speech)