Exploiting the heightened phase synchrony in patients with neuromuscular disease for the establishment of efficient motor imagery BCIs.
Kostas Georgiadis, Nikos Laskaris, Spiros Nikolopoulos and 1 others
PMID 30373619WHAT IT FOUND
Six people with neuromuscular disease showed stronger brain synchrony than six controls, and their imagined left or right hand movements were decoded more accurately without prior BCI experience.
This was an offline experiment, not a tested therapy.
Key findings
01Participants with neuromuscular disease showed stronger brain connectivity than controls, even while resting.
02In the left versus right movement imagination task, five of six patients exceeded 75% accuracy, and half the controls never exceeded 60%.
03In simulated self-paced testing, false-positive rates ranged from 2.2% to 7.2% and false-negative rates from 1.4% to 5.3%.
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
Only 12 participants and 40 trials per participant were analysed, so the findings are preliminary. The self-paced BCI result was a simulation using resting-state recordings, not actual self-initiated movement. All decoding was offline with cleaned EEG; real-time robustness to artefacts such as blinks was not shown. The method needed subject-specific training data, so it is not a no-training clinical tool. Connectivity was measured at sensor level and volume conduction was not addressed. No patient-important functional outcome was measured; the outcome was classification of imagined hand movement.
Declared interests
Horizon 2020 is listed as the funder. The supplied text does not include a conflicts-of-interest statement.
The easy way to misread this
Do not read this as evidence that motor imagery BCIs improve communication, movement, or daily function in neuromuscular disease. The study was an offline experiment in 12 people, and the self-paced part was simulated rather than tested with real user-initiated movement.