Epileptic seizures result from abnormal brain activity, posing significant health risks due to their sudden and unpredictable nature. Accurate seizure prediction is crucial for improving patient outcomes and enabling timely interventions. Recent advancements in artificial intelligence (AI), particularly in machine learning (ML) and deep learning (DL), have significantly enhanced seizure detection and prediction. This review provides a comprehensive overview of seizure prediction models that integrate temporal and spectral features as inputs or enhanced representations for ML and DL models. Emphasizing convolutional neural networks (CNNs) and other deep architectures, we explore the role of time-domain and frequency-domain features, such as wavelet transforms, short-time Fourier transforms, and spectrogram representations, in improving model performance. Additionally, the review discusses common challenges, including feature interpretability, generalizability across datasets, and computational efficiency. By highlighting recent advancements and limitations, this study provides insights into optimizing spectral and temporal feature integration for seizure prediction, paving the way for more robust and clinically viable AI-based solutions.

Seizure prediction is a critical challenge in epilepsy management, offering the potential to improve patient outcomes through timely interventions. This study proposes a novel framework combining a convolutional neural network (CNN) based on EfficientNet-B0 and an ensemble of six Support Vector Machines (SVMs) with a voting mechanism for robust seizure prediction. The framework leverages normalized Short-Time Fourier Transform (STFT) and channel correlation features extracted from EEG signals to capture both spectral and spatial information. The methodology was validated on the CHB-MIT dataset across preictal windows of 10, 20, and 30 min, achieving accuracies of 96.12%, 94.89%, and 94.21%, and sensitivities of 95.21%, 93.98%, and 93.55%, respectively. Comparing the results with state-of-the-art methods, we highlight the framework’s robustness and adaptability. The EfficientNet-B0 backbone ensures high accuracy with computational efficiency, while the SVM ensemble enhances prediction reliability by mitigating noise and variability in EEG data.