Biology subjects

Paillard, J.

Publications and source records attributed to Paillard, J..

3 recordsLinked to original sources

bioRxiv2025

Neurologically altered brain activity may not look like aged brain activity: Implications for brain-age modeling and biomarker strategies

BackgroundBrain-age gap (BAG), the difference between predicted age and chronological age, is studied as a biomarker for the natural progression of neurodegeneration. The BAG captures brain atrophy as measured with structural Magnetic Resonance Imaging (MRI). Electroencephalography (EEG) has also been explored as a functional means for estimating brain age. However, EEG studies showed mixed results for BAG including a seemingly paradoxical negative BAG, i.e. younger predicted age than chronological age, in neurological populations. ObjectivesThis study critically examined brain age estimation from spectral EEG power as common measure brain activity in two of the largest public EEG datasets containing neurological cases alongside controls. MethodsEEG recordings were analyzed from individuals with neurological conditions (n=900, TUAB data; n=417 MCI & n=311 dementia, CAU data) and controls (n=1254, TUAB data; n=459, CAU data). ResultsWe found that age-prediction models trained on the reference population systematically under-predicted age in people with neurological conditions replicating a negative BAG for diseased brain activity. Inspection of age-related trends along the EEG power spectra revealed complex frequency-dependent alterations in neurological groups underlying the seemingly paradoxical negative BAG. ConclusionsThe utility of brain age as an interpretable biomarker relies on the observation from structural MRI that progressive neurodegeneration often broadly resembles accelerated aging. This assumption can be violated for functional assessments such as EEG spectral power and, potentially, different neurological and psychiatric conditions or therapeutic effects. The sign of the BAG may not meaningfully be interpreted as a deviation from normal aging.

neuroscience↗

bioRxiv2024

GREEN: a lightweight architecture using learnable wavelets and Riemannian geometry for biomarker exploration

Spectral analysis using wavelets is widely used for identifying biomarkers in EEG signals. At the same time, Riemannian geometry enabled theoretically grounded machine learning models with high performance for predicting biomedical outcomes from multichannel EEG recordings. However, these methods often rely on handcrafted rules and sequential optimization. In contrast, deep learning (DL) offers end-to-end trainable models that achieve state-of-the-art performance on various prediction tasks but lack interpretability and interoperability with established neuroscience concepts. We introduce GREEN (Gabor Riemann EEGNet), a lightweight neural network that integrates wavelet transforms and Riemannian geometry for processing raw EEG data. Benchmarking on five prediction tasks (age, sex, eyes-closed detection, dementia diagnosis, EEG pathology) across three datasets (TUAB, CAUEEG, TDBRAIN) with over 5000 participants, GREEN outperformed non-deep state-of-the-art models and performed favorably against large DL models on the CAU benchmark using orders of magnitude fewer parameters. Computational experiments showed that GREEN facilitates learning sparse representations without compromising performance. The modularity of GREEN allows for the computation of classical measures of phase synchrony, such as pairwise phase-locking values, which are found to convey information for dementia diagnosis. The learned wavelets can be interpreted as bandpass filters, enhancing explainability. We illustrate this with the Berger effect, demonstrating the modulation of 8-10 Hz power when closing the eyes. By integrating domain knowledge, GREEN achieves a desirable complexity-performance trade-off and learns interpretable EEG representations. The source code is publicly available.

neuroscience↗

bioRxiv2023

Machine learning of brain-specific biomarkers from EEG

Electroencephalography (EEG) has a long history as a clinical tool to study brain function, and its potential to derive biomarkers for various applications is far from exhausted. Machine learning (ML) can guide future innovation by harnessing the wealth of complex EEG signals to isolate relevant brain activity. Yet, ML studies in EEG tend to ignore physiological artifacts, which may cause problems for deriving biomarkers specific to the central nervous system (CNS). We present a framework for conceptualizing machine learning from CNS versus peripheral signals measured with EEG. A common signal representation across the frequency spectrum based on Morlet wavelets allowed us to define traditional brain activity features (e.g. log power) and alternative inputs used by state-of-the-art ML approaches (covariance matrices). Using more than 2600 EEG recordings from large public databases (TUAB, TDBRAIN), we studied the impact of peripheral signals and artifact removal techniques on ML models in exemplary age and sex prediction analyses. Across benchmarks, basic artifact rejection improved model performance whereas further removal of peripheral signals using ICA decreased performance. Our analyses revealed that peripheral signals enable age and sex prediction. However, they explained only a fraction of the performance provided by brain signals. We show that brain signals and body signals, both reflected in the EEG, allow for prediction of personal characteristics. While these results may depend on specific prediction problems, our work suggests that great care is needed to separate these signals when the goal is to develop CNS-specific biomarkers using ML.

neuroscience↗