Cognitive Load Estimation Using Brain Foundation Models and Interpretability for BCIs
This work addresses the need for accurate and interpretable cognitive load monitoring in BCIs, which is crucial for adaptive user interfaces and personalized learning.
The authors propose using Brain Foundation Models (BFMs) for real-time cognitive load estimation from EEG, achieving improved accuracy over state-of-the-art methods by fine-tuning a small subset of layers, while also providing interpretability via Partition SHAP.
Accurately monitoring cognitive load in real time is critical for Brain-Computer Interfaces (BCIs) that adapt to user engagement and support personalized learning. Electroencephalography (EEG) offers a non-invasive, cost-effective modality for capturing neural activity, though traditional methods often struggle with cross-subject variability and task-specific preprocessing. We propose leveraging Brain Foundation Models (BFMs), large pre-trained neural networks, to extract generalizable EEG features for cognitive load estimation. We adapt BFMs for long-term EEG monitoring and show that fine-tuning a small subset of layers yields improved accuracy over the state-of-the-art. Despite their scale, BFMs allow for real-time inference with a longer context window. To address often-overlooked interpretability challenges, we apply Partition SHAP (SHapley Additive exPlanations) to quantify feature importance. Our findings reveal consistent emphasis on prefrontal regions linked to cognitive control, while longitudinal trends suggest learning progression. These results position BFMs as efficient and interpretable tools for continuous cognitive load monitoring in real-world BCIs.