medRxivJClub
Restoring intended speech in people with dysarthria from pontine stroke using an intracortical brain-computer interface
medRxiv · · Preprint · Open access
Nason-Tomaszewski, Deevi + 19 more
Abstract ↗AI summary
The abstract is read at the publisher; the summary is JClub's.
Intracortical brain-computer interfaces can decode intended speech in people with pontine stroke–related dysarthria using as few as one 64-channel microelectrode array, reaching 19.4% WER (125,000 words) for T16.
- Why it matters: Communication restoration after pontine stroke–induced dysarthria is still difficult, and it is unclear whether iBCI speech gains seen in ALS transfer to this stroke population.
- What they did: BrainGate2 participants T16 and T22 used iBCI signals to predict word sequences from mouthed sentences from a large vocabulary, with neural networks and standard signal-change adjustments.
- The result: Decoding stayed stable more than two years for T16 and two months for T22, yielding median 19.4% and 10.6% WERs (125,000 words) and 10.0% and 2.25% WERs (1,024 words), enabling high-performance brain-to-text communication.
The findingWhy it mattersWhat they didThe result
AI summary of the abstract · may contain errors · not medical advice · read the paper.
- Open access
- 6 cites