Interpretable EEG biomarkers with bag-of-waves: Spatial and temporal waveform dictionaries for low-data regimes

2026-07-24

AI Summary

Traditional EEG analysis is hindered by strong prior biases from predefined spectral features or the data dependency and lack of interpretability inherent in deep models, particularly under low-data conditions. This work proposes a bag-of-waves framework that learns a small, interpretable dictionary of EEG waveform atoms via unsupervised, translation-invariant k-means, converting continuous signals into symbolic sequences. Temporal structure is captured through n-gram modeling, while spatial information is incorporated using single-channel, regional, and cross-channel atomic representations. For the first time, this approach integrates an interpretable waveform dictionary, n-gram temporal modeling, and multi-channel spatial extension, achieving performance on par with state-of-the-art deep models under extremely limited data while using significantly fewer parameters. The method explicitly recovers neurophysiologically verifiable canonical waveforms across three datasets: mouse genotype clustering, dementia resting-state classification, and six-class clinical event detection on TUEG.

Abstract

Electroencephalography (EEG) is widely used to diagnose neurological conditions, but its analysis usually relies on either predefined spectral features or deep neural networks. Predefined features carry a strong bias, since they fix in advance what counts as informative, while deep neural networks and foundation models are hard to interpret and need large amounts of data and compute. We present bag-of-waves, an interpretable framework that learns a small dictionary of recurring EEG waveform templates, called atoms, using shift-invariant k-means without labels. The continuous EEG is then turned into a sequence of atom tokens, whose counts feed a simple downstream classifier or clustering step. We extend this representation in two ways: we add atom-to-atom transitions, which we call n- grams, to capture temporal structure, and we move from single-channel atoms to regional and cross-channel spatial atoms for the multichannel case. We test the method on three complementary datasets, each probing a different aspect: single-channel mouse genotype clustering with only sixteen animals (the low-data and temporal case), resting-state dementia classification (the spatial case), and the TUEV benchmark, a six-way classification of clinical EEG events (a high-data comparison against strong deep and foundation baselines). Across all three datasets, bag-of-waves achieves performance competitive with state-of-the-art deep and foundation models. Yet, it operates with a fraction of the parameter count and provides full interpretability: because every atom corresponds to an inspectable waveform, the method explicitly recovers known clinical morphologies that a neurophysiologist can directly validate. Its main advantage is that it works in the low-data regime where heavier models are a poor fit.

Problem

• EEG
• interpretability
• low-data regime
• biomarkers
• neurological diagnosis

Innovation

• bag-of-waves
• interpretable EEG biomarkers
• shift-invariant k-means
• low-data regime
• spatiotemporal waveform dictionaries