Statistical Validation of EEG Signal Variability in Epilepsy Monitoring

Hameed, Maan; Jassim, Saja; Prasad, Nabaa

doi:10.25673/123768

Proceedings of International Conference on Applied Innovation in IT · 2026/03/31 · Vol. 14 · Issue 1 · pp. 1491–1497

Statistical Validation of EEG Signal Variability in Epilepsy Monitoring

Maan Hameed, Saja Tawfeeq Jassim, Nabaa Ahmed Noori and Amrita Prasad

📄 Download PDF DOI: 10.25673/123768

Abstract

Epilepsy is a prevalent neurological disorder requiring reliable biomarkers for effective diagnosis and continuous monitoring. Electroencephalography (EEG) remains the gold standard, yet reproducibility and interpretability of derived metrics remain limited. This study aims to statistically validate EEG variability measures as potential biomarkers for epilepsy monitoring. Public EEG datasets, including CHB-MIT and TUH, were preprocessed using standard pipelines involving band-pass and notch filtering, ICA-based artifact rejection, and segmentation into 10-second epochs. Variability indices spanning time-domain (coefficient of variation, RMSSD), frequency-domain (band power variability), and nonlinear measures (sample entropy, permutation entropy) were extracted. Statistical validation included intraclass correlation coefficients (ICC), Bland-Altman analysis, minimal detectable change (MDC), and receiver operating characteristic (ROC) analysis. Results revealed excellent reliability for coefficient of variation and band power variability (ICC > 0.80) and moderate reproducibility for entropy-based metrics (ICC ≈ 0.70). ROC analysis showed band power variability achieving AUC = 0.83, confirming clinical discrimination between peri-ictal and interictal states. These findings demonstrate that variability metrics can serve as reproducible and clinically actionable biomarkers.

Keywords

EEG Variability Epilepsy Monitoring Reliability Reproducibility Entropy ROC Analysis Biomarkers Statistical Validation.

References

Y. Höller, K. Butz, A. Thomschewski, E. Schmid, A. Uhl, A. C. Bathke, and E. Trinka, “Reliability of EEG interactions differs between measures and is specific for neurological diseases,” Frontiers in Human Neuroscience, vol. 11, p. 350, 2017.
Y. Höller, A. Uhl, A. Bathke, A. Thomschewski, K. Butz, R. Nardone, and E. Trinka, “Reliability of EEG measures of interaction: a paradigm shift is needed to fight the reproducibility crisis,” Frontiers in Human Neuroscience, vol. 11, p. 441, 2017.
J. Batista, M. F. Pinto, M. Tavares, F. Lopes, A. Oliveira, and C. Teixeira, “EEG epilepsy seizure prediction: the post-processing stage as a chronology,” Scientific Reports, vol. 14, no. 1, p. 407, 2024.
M. I. da Silva Tavares, “EEG epilepsy seizure prediction: the post-processing stage as a chronology,” Master’s thesis, Universidade de Coimbra, 2021.
S. A. Karthik, K. N. Bharath, B. R. Ramji, K. Puttegowda, B. Aruna, and D. S. Kumar, “Enhanced EEG signal processing for accurate epileptic seizure detection,” SN Computer Science, vol. 6, no. 6, p. 608, 2025.
L. T. Nguyen and M. Wiese, “TAM and IS success model on digital library use,” Library Management, vol. 24, no. 1-2, pp. 173-185, 2003, [Online]. Available: https://doi.org/10.1108/01435120310454592.
Y. Zhang, H. Li, and X. Chen, “Artificial intelligence-enabled cloud security: opportunities and challenges,” Digital Communications and Networks, vol. 11, no. 2, pp. 55-66, 2025, [Online]. Available: https://doi.org/10.1016/j.dcan.2025.01.005.
A. Al Farawn, S. Al-Khammasi, A. H. Alhilali, and N. S. Ali, “EEG feature selection techniques for epileptic seizure detection: performance and evaluation study,” International Journal of Mathematics, Statistics, and Computer Science, vol. 3, pp. 345-358, 2025.
E. Aanestad, S. Beniczky, H. Olberg, and J. Brøgger, “Unveiling variability: a systematic review of reproducibility in visual EEG analysis, with focus on seizures,” Epileptic Disorders, vol. 26, no. 6, pp. 827-839, 2024.
A. Jain, R. Raja, S. Srivastava, P. C. Sharma, J. Gangrade, and M. R., “Analysis of EEG signals and data acquisition methods: a review,” Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, vol. 12, no. 1, p. 2304574, 2024.
P. Myers, K. M. Gunnarsdottir, A. Li, V. Razskazovskiy, J. Craley, A. Chandler, and K. S. Husari, “Diagnosing epilepsy with normal interictal EEG using dynamic network models,” Annals of Neurology, vol. 97, no. 5, pp. 907-918, 2025.
G. Bertazzoli, E. Dognini, P. J. Fried, C. Miniussi, P. Julkunen, and M. Bortoletto, “Bridging the gap to clinical use: a systematic review on TMS-EEG test-retest reliability,” Clinical Neurophysiology, 2025.
M. A. Bahhah and E. T. Attar, “Enhancing epilepsy seizure detection through advanced EEG preprocessing techniques and peak-to-peak amplitude fluctuation analysis,” Diagnostics, vol. 14, no. 22, p. 2525, 2024.
J. F. Restrepo, D. M. Mateos, and J. M. D. López, “A transfer entropy-based methodology to analyze information flow under eyes-open and eyes-closed conditions with a clinical perspective,” Biomedical Signal Processing and Control, vol. 86, p. 105181, 2023.
S. Kumar and R. Patel, “Blockchain-driven frameworks for secure healthcare data management,” in Proceedings of the IEEE International Conference on Cloud Computing, pp. 1-8, 2025, [Online]. Available: https://doi.org/10.1109/11015778.