Disentangling EEG Fingerprinting and Sleep Biomarkers Using Generalized Weighted Ordinal Patterns.

Background: Electroencephalographic (EEG) recordings simultaneously contain information about neurophysiological dynamics and subject-specific characteristics. While this duality may enable biomarker discovery and individual identification, it also raises concerns that machine-learning models may achieve high predictive performance by exploiting subject identity rather than physiologically relevant information. Methods: In this study, we investigated whether generalized weighted ordinal patterns (GWOP), a statistical-complexity representation incorporating both temporal ordering and amplitude fluctuations, support sleep-stage classification while minimizing identity-related confounding. Sleep EEG recordings from 31 healthy subjects were segmented into 30-s epochs and represented using 3150 GWOP features derived from multiple embedding dimensions, time delays, and entropic indices. XGBoost classifiers were evaluated under intra-subject and inter-subject validation schemes to quantify the impact of EEG fingerprinting on sleep-stage classification performance. An additional subject-identification analysis was conducted using the same feature representation. Results: Sleep-stage classification generalized well to previously unseen subjects, with accuracy decreasing only from 79.2% to 75.8% between intra-subject and inter-subject evaluations. Feature-importance analysis using SHAP revealed an almost perfect correspondence between the features driving classification in both validation schemes (Spearman ρ=0.998). Conclusions: While this suggests that the models effectively generalize across subjects without being heavily confounded by individual identities, it indicates a framework of partial separation rather than complete orthogonality across the global feature space. In contrast, GWOP features also supported subject identification with 63.9% accuracy across the 31 individuals, demonstrating that GWOP preserve substantial fingerprinting information. The most informative features for subject identification showed little overlap with those governing sleep-stage classification, suggesting a partial separation between identity-related and biomarker-related information within the same feature space. These findings suggest that EEG fingerprinting and biomarker extraction are not necessarily competing objectives and support GWOP-based statistical-complexity measures as a promising proof-of-concept framework for robust sleep EEG analysis, serving as a foundation for future scale-up precision-neuroscience applications.