Evaluating person-centered factors associated with brain-computer interface access to a commercial augmentative and alternative communication paradigm.
Kevin M Pitt, Jonathan S Brumberg
PMID 33667154WHAT IT FOUND
Four people with ALS tried a brain-computer interface to spell on a standard AAC keyboard.
Two achieved accuracy matching healthy controls, but performance varied widely and no one reached the threshold for free spelling.
Key findings
01Two participants with ALS achieved BCI-AAC accuracy levels within the range of neurotypical controls, while one participant showed no improvement.
02Participants with suspected cognitive impairment but less motor loss performed best, suggesting motor ability may be a stronger predictor of success than cognition in this context.
03No participant with ALS reached the accuracy threshold required to move from copy spelling to free spelling tasks during the study.
STILL TO COME
How it was doneWhat they foundWhat it means for PTsWhat it means for OTsWhat it means for SLPs
Read the rest of this summary
You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.
What it does not show
The sample size is extremely small (4 ALS participants), limiting generalizability. The BCI system was not individualized or adapted for each participant’s specific needs, which may have hindered performance. No participants reached the threshold for functional free spelling, so real-world communication outcomes were not measured. The study did not test other BCI modalities (e.g., P300 or eye-gaze hybrids) that might suit different profiles better. Medication and food intake effects on performance were not controlled or measured, only self-reported time since last meal.
Declared interests
The authors declared no conflicts of interest. The study was supported by non-U.S. government and NIH extramural grants.
The easy way to misread this
Do not assume that a patient’s cognitive screen score predicts their ability to use a BCI. Two participants with suspected cognitive impairment achieved the highest accuracy, while those with intact cognition did not necessarily perform better.