The use of Multi-domain Electroencephalogram Representations in the building of Models based on Convolutional and Recurrent Neural Networks for Epilepsy Detection

2025-04-24

AI Summary

Epileptic seizure detection suffers from high inter-rater variability and subjectivity in manual EEG interpretation. Method: This study systematically evaluates the impact of time-domain, frequency-domain, and time-frequency-domain EEG representations on CNN and RNN performance, employing ANOVA with post-hoc tests to quantitatively assess representational efficacy. Contribution/Results: We first demonstrate—quantitatively—that frequency-domain features (via FFT) significantly outperform alternatives and synergize optimally with CNNs. Evaluated on standard public datasets, the frequency-domain CNN achieves 97.2% accuracy, 97.5% sensitivity, and 97.0% specificity, substantially surpassing time-domain and time-frequency-domain baselines in robustness and generalizability. This work establishes a principled paradigm for optimal input representation and architecture selection in automated epilepsy detection, delivering an interpretable, highly reliable deep learning framework for clinical decision support.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Computer Vision: Representation Learning for Vision
• Machine Learning: Representation Learning

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Epilepsy, affecting approximately 50 million people globally, is characterized by abnormal brain activity and remains challenging to treat. The diagnosis of epilepsy relies heavily on electroencephalogram (EEG) data, where specialists manually analyze epileptiform patterns across pre-ictal, ictal, post-ictal, and interictal periods. However, the manual analysis of EEG signals is prone to variability between experts, emphasizing the need for automated solutions. Although previous studies have explored preprocessing techniques and machine learning approaches for seizure detection, there is a gap in understanding how the representation of EEG data (time, frequency, or time-frequency domains) impacts the predictive performance of deep learning models. This work addresses this gap by systematically comparing deep neural networks trained on EEG data in these three domains. Through the use of statistical tests, we identify the optimal data representation and model architecture for epileptic seizure detection. The results demonstrate that frequency-domain data achieves detection metrics exceeding 97%, providing a robust foundation for more accurate and reliable seizure detection systems.

Problem

• Identifying optimal EEG data representation for epilepsy detection
• Comparing deep neural networks across time, frequency, and time-frequency domains
• Improving automated seizure detection accuracy beyond 97% metrics

Innovation

• Multi-domain EEG representations for epilepsy detection
• Convolutional and Recurrent Neural Networks combined
• Frequency-domain data achieves over 97% accuracy