TL;DR
A clinically interpretable aEEG-CSA algorithm is feasible for neonatal seizure detection by extracting standard EEG features and coupling these features with a supervised ML classifier.
A Deep Hybrid Neural Network framework that combines Convolutional Neural Networks (CNN) with the Aquila Optimizer (AO) for the automatic detection of epileptic seizures utilizing EEG data in MATLAB is introduced.
Epilepsy and migraine are prone to clinical misdiagnosis due to overlapping clinical manifestations, while the limited availability of electroencephalogram (EEG) data further complicates accurate differential diagnosis. To address this challenge, this study proposes a three-class classification framework for epilepsy, migraine, and healthy controls based on EEG signals collected from 36 participants. After preprocessing the raw EEG data with a 0.5–60 Hz bandpass filter, 15 features were extracted, including 12 statistical features and three nonlinear dynamical features. Four machine learning models, namely support vector machine (SVM), random forest (RF), LightGBM, and XGBoost, were systematically evaluated for classification performance. Among them, XGBoost achieved the best overall results, with a test accuracy of 0.90 and superior performance across all major evaluation metrics. Feature importance analysis based on the gain metric of XGBoost identified the Hurst exponent as the most influential feature. Notably, its inter-group distribution differences were highly consistent with the pathological characteristics of epilepsy and migraine. These findings suggest that EEG-based feature fusion combined with machine learning provides an effective strategy for multi-class neurological disease classification, and that the Hurst exponent may serve as a promising biomarker for the differential diagnosis of epilepsy and migraine.
This study systematically introduces and evaluates 25 less-explored time-domain features, 13 of which have no documented precedent as classification features in scalp EEG seizure detection, against 25 classical features and their 50-feature combination.
A compact composite feature termed the Seizure Intensity Index (SII) together with an extended representation incorporating additional theta and alpha band descriptors is proposed together with an extended representation incorporating additional theta and alpha band descriptors for cross-patient seizure detection.
Due to EEG overlap, brain tumour-induced seizures (BTIS) and primary epileptic seizures (ES) are difficult to distinguish. This paper introduces an AI-enhanced BCI model that uses hybrid deep learning architectures to differentiate accurately. We used CNNs for spatial feature extraction and Transformer-based attention mechanisms for temporal dependency modelling to decompose multi-channel EEG data using wavelet and Fourier methods. On a multi-centre dataset of 1,240 EEG sessions (500 subjects: 125 healthy controls, 187 epileptic, 188 tumour-induced seizure cases), our model had 96.7% sensitivity, 94.5% specificity, and 95.6% accuracy. The framework performed well across patient demographics and seizure types. Real-time lightweight architecture detection latency was 8.3 seconds with 0.62 false alarms per day. This study fills a clinical need by offering an automated, interpretable diagnostic tool that may improve seizure treatment and tumour-related neurological consequences.