Case ReportJournal of neuroengineering and rehabilitation2022

Neural correlates of user learning during long-term BCI training for the Cybathlon competition.

Stefano Tortora, Gloria Beraldo, Francesco Bettella and 8 others

PMID 35790978

WHAT IT FOUND

One man with severe weakness learned to control a brain-computer interface for a racing game.

His performance improved over months and remained stable after a one-year break without using the device. This single case suggests skill retention is possible, but does not prove the method works for others.

Key findings

01The participant's race completion time significantly decreased over the training period, from an average of 242.89 seconds in the first 15 runs to 209.93 seconds in the last 15 runs of 2019.

02After a one-year break from using the brain-computer interface, the participant's performance remained stable, with no significant difference between the end of 2019 training and the start of 2020 training.

03The participant achieved competition records and won gold medals in both the 2019 and 2020 Cybathlon BCI events, with race times of 175 seconds and 172 seconds respectively.

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.

Already have one?

What it does not show

The study reports on a single participant, so the findings cannot be generalized to other patients with motor disabilities. The study was observational and uncontrolled, with no comparison group receiving a different training protocol. The participant was a paralympic athlete and had prior experience with competitions, which may influence his ability to handle stress and learn the task compared to a typical patient. The authors note that the lack of decoder recalibration in the second year makes it difficult to separate user learning from machine adaptation, although they argue this was intentional to test user retention.

Declared interests

Funding was provided by the Department of Information Engineering at the University of Padova, the Italian Ministry of Education, University and Research, REACT-EU, the Horizon 2020 Framework Programme, and the Italian Ministry of Foreign Affairs and International Cooperation. No specific commercial conflicts of interest were declared.

The easy way to misread this

Do not assume that this training protocol will lead to similar skill retention or competition-level performance in your patients. This is a single case report of a highly motivated, experienced paralympic athlete, and the results may not apply to individuals with different levels of motor impairment, cognitive status, or training access.

Read it on PubMed →


The study

Participants
1
Certainty of evidence
Very low

Browse

    Cite

    Stefano Tortora, Gloria Beraldo, Francesco Bettella, et al. Neural correlates of user learning during long-term BCI training for the Cybathlon competition. Journal of neuroengineering and rehabilitation. 2022.

    Read the original