Fine-Tuning Strategies for Continual Online EEG Motor Imagery Decoding: Insights from a Large-Scale Longitudinal Study

TL;DR

This study explores effective fine-tuning and online adaptation strategies for improving longitudinal EEG motor imagery decoding across many users and sessions, enhancing stability and performance in real-world brain-computer interfaces.

Contribution

It is the first large-scale longitudinal study to compare fine-tuning strategies and incorporate online test-time adaptation for EEG MI decoding.

Findings

Successive fine-tuning improves performance and stability.

OTTA enables calibration-free adaptation across sessions.

Combining fine-tuning with OTTA enhances long-term decoder robustness.

Abstract

This study investigates continual fine-tuning strategies for deep learning in online longitudinal electroencephalography (EEG) motor imagery (MI) decoding within a causal setting involving a large user group and multiple sessions per participant. We are the first to explore such strategies across a large user group, as longitudinal adaptation is typically studied in the single-subject setting with a single adaptation strategy, which limits the ability to generalize findings. First, we examine the impact of different fine-tuning approaches on decoder performance and stability. Building on this, we integrate online test-time adaptation (OTTA) to adapt the model during deployment, complementing the effects of prior fine-tuning. Our findings demonstrate that fine-tuning that successively builds on prior subject-specific information improves both performance and stability, while OTTA effectively adapts the model to evolving data distributions across consecutive sessions, enabling calibration-free operation. These results offer valuable insights and recommendations for future research in longitudinal online MI decoding and highlight the importance of combining domain adaptation strategies for improving BCI performance in real-world applications. Clinical Relevance: Our investigation enables more stable and efficient long-term motor imagery decoding, which is critical for neurorehabilitation and assistive technologies.