Related Experiment Video
Updated: May 7, 2026
P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation
Published on: September 8, 2023
A comparison of two spelling Brain-Computer Interfaces based on visual P3 and SSVEP in Locked-In Syndrome
Adrien Combaz1, Camille Chatelle, Arne Robben
1Computational Neuroscience Group, Laboratory for Neuro- and Psychophysiology, KU Leuven, Leuven, Belgium.
Objectives:
We study the applicability of a visual P3-based and a Steady State Visually Evoked Potentials (SSVEP)-based Brain-Computer Interfaces (BCIs) for mental text spelling on a cohort of patients with incomplete Locked-In Syndrome (LIS).
Methods:
Seven patients performed repeated sessions with each BCI. We assessed BCI performance, mental workload and overall satisfaction for both systems. We also investigated the effect of the quality of life and level of motor impairment on the performance.
Results:
All seven patients were able to achieve an accuracy of 70% or more with the SSVEP-based BCI, compared to 3 patients with the P3-based BCI, showing a better performance with the SSVEP BCI than with the P3 BCI in the studied cohort. Moreover, the better performance of the SSVEP-based BCI was accompanied by a lower mental workload and a higher overall satisfaction. No relationship was found between BCI performance and level of motor impairment or quality of life.
Conclusion:
Our results show a better usability of the SSVEP-based BCI than the P3-based one for the sessions performed by the tested population of locked-in patients with respect to all the criteria considered. The study shows the advantage of developing alternative BCIs with respect to the traditional matrix-based P3 speller using different designs and signal modalities such as SSVEPs to build a faster, more accurate, less mentally demanding and more satisfying BCI by testing both types of BCIs on a convenience sample of LIS patients.
