Cybathlon experiences of the Graz BCI racing team Mirage91 in the brain-computer interface discipline.
Karina Statthaler, Andreas Schwarz, David Steyrl and 6 others
PMID 29282131WHAT IT FOUND
One pilot with incomplete locked-in syndrome after stroke trained a brain-computer interface, but in the race it repeatedly chose one command, and he failed to qualify.
Key findings
01The pilot's best offline four-task BCI combination was right hand, both feet, mental subtraction and rest, with peak accuracy of 75.6%.
02Online feedback BCI performance peaked at 63.1%, a drop from offline screening.
03At the race, the system was strongly biased toward one class, giving a 196-second runtime and failure to qualify.
STILL TO COME
How it was doneWhat they found
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
It describes one pilot, so it is not evidence that a BCI improves patient function or that a treatment works. The pilot was also receiving rehabilitation therapies at the centre, so the contribution of BCI training alone cannot be separated. The reported outcomes are engineering performance and race results, not clinical outcomes such as communication, mobility, or daily activity. The competition failure was analysed after the event, and the paper reports future plans rather than tested fixes for that failure.
Declared interests
The paper lists Horizon 2020 and the European Research Council as funders. It also identifies VAMED as a sponsor and says VAMED produced a promotional video about the team and pilot.
The easy way to misread this
Do not read this as proof that BCI training improves communication, mobility, or daily function after stroke. It is a single case report of an engineering team's competition experience, and the system failed during the race.