Interpretable EEG biomarkers with bag-of-waves: Spatial and temporal waveform dictionaries for low-data regimes
2026-07-24 • Machine Learning
Machine Learning
AI summaryⓘ
The authors created a new way to analyze EEG brain signals called bag-of-waves. Instead of relying on preset features or complex neural networks, their method finds small, repeating wave patterns (atoms) automatically and uses these to classify or group EEG data. They tested it on different datasets, from mice to human brain disorders, and found it works nearly as well as deep learning but is simpler and easier to understand. This approach is especially useful when there isn’t much data, and its results can be checked directly by experts because the wave patterns are human-interpretable.
Electroencephalography (EEG)Waveform templatesShift-invariant k-meansTokenizationn-gramsMultichannel EEGInterpretabilityLow-data regimeDementia classificationNeural networks
Authors
Athanasios Papastathopoulos-Katsaros, Steven T. Lee, Lin Yao, Ajay Thomas, Junseok Park, Matthew J. McGinley, Zhandong Liu
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.