Robust and Clinically Reliable EEG Biomarkers: A Cross Population Framework for Generalizable Parkinson's Disease Detection

A team of researchers from multiple institutions, led by Nicholas R. Rasmussen, has published a preprint on arXiv proposing a novel framework for developing robust and clinically reliable EEG biomarkers for Parkinson's disease (PD) detection. The key innovation is a population-aware evaluation framework that explicitly addresses cross-population generalization in multi-site settings. Traditional models trained under i.i.d. assumptions often capture population-specific artifacts rather than disease-relevant neural structure, leading to poor generalization across clinical cohorts—a problem amplified by EEG's low signal-to-noise ratio and heterogeneous acquisition conditions.

The framework uses an n-gram expansion strategy to enumerate all cross-population train-test configurations across five independent cohorts, resulting in 75 directional evaluations. A nested cross-validation design with integrated channel selection ensures prospective biomarker identification without population leakage. Results show that cross-population transfer is asymmetric and that both accuracy and biomarker stability improve with increasing training population diversity, achieving up to 94.1% accuracy on held-out cohorts. A theoretical analysis based on mixture risk optimization and hypothesis space contraction explains these trends, showing that multi-population training promotes population-robust representations. This work establishes a principled framework for learning generalizable EEG biomarkers for multi-site biomedical applications, potentially improving PD diagnosis across diverse clinical settings.