Seizure Type Classification Based on Hybrid Feature Engineering and Mutual Information Analysis Using Electroencephalogram

TL;DR

This paper presents a new framework for classifying seizure types using EEG data with improved accuracy through hybrid feature engineering and mutual information analysis.

Contribution

The novel contribution is a hybrid framework combining multi-band EEG feature engineering and mutual information analysis for accurate seizure type classification.

Findings

XGBoost achieved the highest performance with accuracy 0.8710, F1 score 0.8721, and AUC 0.9797.

γ-band features were found to be most important for classification.

The framework showed robust discrimination but noted overlaps in focal seizure subtypes.

Abstract

Epilepsy has diverse seizure types that challenge diagnosis and treatment, requiring automated and accurate classification to improve patient outcomes. Traditional electroencephalogram (EEG)-based diagnosis relies on manual interpretation, which is subjective and inefficient, particularly for multi-class differentiation in imbalanced datasets. This study aims to develop a hybrid framework for automated multi-class seizure type classification using segment-wise EEG processing and multi-band feature engineering to enhance precision and address data challenges. EEG signals from the TUSZ dataset were segmented into 1-s windows with 0.5-s overlaps, followed by the extraction of multi-band features, including statistical measures, sample entropy, wavelet energies, Hurst exponent, and Hjorth parameters. The mutual information (MI) approach was employed to select the optimal features, and seven machine learning models (SVM, KNN, DT, RF, XGBoost, CatBoost, LightGBM) were evaluated via 10-fold stratified cross-validation with a class balancing strategy. The results showed the following: (1) XGBoost achieved the highest performance (accuracy: 0.8710, F1 score: 0.8721, AUC: 0.9797), with γ-band features dominating importance. (2) Confusion matrices indicated robust discrimination but noted overlaps in focal subtypes. This framework advances seizure type classification by integrating multi-band features and the MI method, which offers a scalable and interpretable tool for supporting clinical epilepsy diagnostics.

Figures