Evaluating the perspectives of those with severe physical impairments while learning BCI control of a commercial augmentative and alternative communication paradigm.
Kevin M Pitt, Jonathan S Brumberg
PMID 34184974WHAT IT FOUND
Experiences varied widely while four people with ALS learned brain-computer spelling: satisfaction followed better control for A1 and A3, and lower frustration for A2 and A4.
Mental effort was high for some, fatigue ratings changed little. This small study cannot show the system works.
Key findings
01How well the device matched intended selections varied: A1 was fair (Kappa = 0.333), A4 was no to slight (.199), A2 was no to slight (0.139), and A3 was below chance (0.01).
02For A1 and A3, satisfaction moved in the same direction as accuracy; for A2 and A4, satisfaction moved in the opposite direction to frustration.
03A1, A2, and A4 described fatigue as physical effort, while A3 described fatigue as mental effort.
STILL TO COME
How it was doneWhat they foundWhat 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
Only four individuals with ALS took part, so the patterns may not apply to other people with ALS or other severe impairments. There was no comparison communication method or control group described, so the study cannot show that BCI-AAC improved communication compared with usual care. Results were analysed within each participant, so they describe individual patterns rather than a group effect. Some participants trained at home and some in a laboratory, and seating and setup differed, so conditions were not identical. The participants could speak and were not all AAC users, so their experience may differ from people who rely on AAC daily.
Declared interests
The supplied article text does not include a conflicts or funding declaration. The journal metadata lists non-U.S. government and NIH extramural research support.
The easy way to misread this
Do not read this as proof that BCI-AAC works for people with ALS. Four participants had different results, and satisfaction was linked to accuracy for some and to frustration for others, with no control group.