Comparing a BCI communication system in a patient with Multiple System Atrophy, with an animal model

Comparing a BCI communication system in a patient with Multiple System Atrophy, with an animal model

Brain Research Bulletin

10.1016/j.brainresbull.2025.111289

https://doi.org/10.1016/j.brainresbull.2025.111289

Brian Premchand, Kyaw Kyar Toe, Chuanchu Wang, Kai Rui Wan, Thevapriya Selvaratnam, Valerie Ethans Toh, Wai Hoe Ng, Camilo Libedinsky, Weiguo Chen, Ruiqi Lim, Ming-Yuan Cheng, Yuan Gao, Kai Keng Ang, Rosa Qi Yue So

Brain-computer interface (BCI), BMI, Multiple System Atrophy, LSTM, neural network, Paralysis

11 March 2025

Premchand, B., Toe, K. K., Wang, C., Wan, K. R., Selvaratnam, T., Toh, V. E., Ng, W. H., Libedinsky, C., Chen, W., Lim, R., Cheng, M.-Y., Gao, Y., Ang, K. K., & So, R. Q. Y. (2025). Comparing a BCI communication system in a patient with Multiple System Atrophy, with an animal model. Brain Research Bulletin, 223, 111289. https://doi.org/10.1016/j.brainresbull.2025.111289

Paralysis affects many people worldwide, and the people affected often suffer from impaired communication. We developed a microelectrode-based Brain-Computer Interface (BCI) for enabling communication in patients affected by paralysis, and implanted it in a patient with Multiple System Atrophy (MSA), a neurodegenerative disease that causes widespread neural symptoms including paralysis. To verify the effectiveness of the BCI system, it was also tested by implanting it in a non-human primate (NHP). Data from the human and NHP were used to train binary classifiers two different types of machine learning models: a Linear Discriminant Analysis (LDA) model, and a Long Short-Term Memory (LSTM)-based Artificial Neural Network (ANN). The LDA model performed at up to 72.7 % accuracy for binary decoding in the human patient, however, performance was highly variable and was much lower on most recording days. The BCI system was able to accurately decode movement vs non-movement in the NHP (accuracy using LDA: 82.7 ± 3.3 %, LSTM: 83.7 ± 2.2 %, 95 % confidence intervals), however it was not able to with recordings from the human patient (accuracy using LDA: 47.0 ± 5.1 %, LSTM: 44.6 ± 9.9 %, 95 % confidence intervals). We discuss how neurodegenerative diseases such as MSA can impede BCI-based communication, and postulate on the mechanisms by which this may occur.

Attribution 4.0 International (CC BY 4.0)

This research / project is supported by the Agency for Science, Technology and Research - Robust Neural Decoding and Control System
Grant Reference no. : EC-2015–216

https://oar.a-star.edu.sg/communities-collections/articles/21621

0361-9230

Institute for Infocomm Research

https://doi.org/10.1016/j.brainresbull.2025.111289