Spectral Priors vs. Attention: Investigating the Utility of Attention Mechanisms in EEG-Based Diagnosis

TL;DR

This study compares spectral feature extraction and attention mechanisms in EEG-based diagnosis, showing spectral features outperform attention in identifying neurodegenerative diseases across multiple datasets.

Contribution

The paper demonstrates that spectral features enhance classification accuracy and that attention mechanisms are limited in capturing stable spectral signatures in EEG data.

Findings

Spectral features enable traditional models to match or outperform deep learning.

Attention mechanisms fail to identify stable spectral signatures.

Frequency-selective features do not significantly improve attention-based models.

Abstract

Electroencephalograph (EEG) timeseries signals are characterized by significant noise and coarse spatial resolution, which complicates the classification of neurodegenerative diseases. Even SOTA deep learning architectures struggle to distinguish between healthy controls and diseased subjects, or between different disease types, due to high intergroup similarity. In this paper, we show that a spectrally selective approach to feature construction enhances class separability. By isolating signal strengths within the primary brainwave bands, we transform high dimensional raw data into high value spectral features. Our results demonstrate that a) features derived from frequency and time frequency domain allow traditional machine learning models to match or exceed the performance of SOTA deep learning models, b) Attention mechanism is unable to distill the stable feature signatures that characterize healthy neural activity in both resting and task EEGs, and c) the limitations of attention based models in finding relevant spectral features appear to be fundamental in that providing frequency selective time domain input do not appreciably improve their performance. We validate our methodology across three open source resting EEG datasets and one task EEG dataset, providing robust empirical evidence for our claims.