Average Rankings Mask Per-Subject Optimality: A Friedman-Nemenyi Benchmark of EEG Motor-Imagery BCI Decoders
Why the best brain-computer interface decoder changes from person to person
Brain-computer interfaces that read motor intention from EEG show no single best decoding method across people, even in ideal conditions. Testing over 1,000 different pipelines on more than 340,000 individual model fits revealed that the top-performing approach varies by dataset and person—matching the decoder to each person's brain patterns improved accuracy by about 7 percentage points compared to using one universal decoder.
Brain-computer interfaces aim to help people with paralysis or locked-in syndrome control prosthetics or communication devices. If one decoding method worked best for everyone, clinical deployment would be straightforward. This work shows that practical BCI systems need to personalize their approach for each user rather than relying on a single universal design, suggesting that real-world BCI performance depends as much on fitting the algorithm to individual brain differences as on the algorithm itself.