Seizure prediction: Methods

Abstract

Epilepsy, one of the most common neurological diseases, affects over 50 million people worldwide. Epilepsy can have a broad spectrum of debilitating medical and social consequences. Although antiepileptic drugs have helped treat millions of patients, roughly a third of all patients have seizures that are refractory to pharmacological intervention. The evolution of our understanding of this dynamic disease leads to new treatment possibilities. There is great interest in the development of devices that incorporate algorithms capable of detecting early onset of seizures or even predicting them hours before they occur. The lead time provided by these new technologies will allow for new types of interventional treatment. In the near future, seizures may be detected and aborted before physical manifestations begin. In this chapter we discuss the algorithms that make these devices possible and how they have been implemented to date. We also compare and contrast these measures, and review their individual strengths and weaknesses. Finally, we illustrate how these techniques can be combined in a closed-loop seizure prevention system.

EEG seizure detection and prediction algorithms: a survey

“…Efforts have also been made to develop seizure prediction algorithms [6,7]. Note that with seizure prediction, it is possible to alert ambulatory patients or caregivers before seizure occurs and causes injury.…”

Multivariate time-series analysis and diffusion maps

“…It is important and desirable to predict seizures so that patients can be warned a few minutes prior. Many studies have been conducted in order to devise reliable methods that can distinguish interictal and preseizure states [18,[42][43][44][45][46][47]. However, because icEEG recordings tend to be very noisy, and because the underlying brain activity states and their relationship to the icEEG activities are unknown, it is considered a difficult problem without existing solutions [42,43].…”

Efficient feature selection using a hybrid algorithm for the task of epileptic seizure detection

“…In general, the use of mathematical models in the discipline of epilepsy seizure falls into two broad categories, namely seizure detection [2] and seizure prediction [3]. In seizure detection, an expert system which is able to differentiate between interictal (normal) and ictal (epileptic) EEG signals is highly desirable.…”

“…Among the machine learning classifiers that are used include extreme learning machine (ELM) [2], support vector machine (SVM) [3], and different types of models of artificial neural networks (ANNs), such as probabilistic neural networks (PNNs) [4], radial basis neural networks (RBNNs) [5], and recurrent neural networks (RNNs) [6]. Each of the classifiers differs in network architecture.…”

“…For example, spectral power features, statistical moments, Hjorth parameter, spectral edge power, wavelet coefficients, Lyapunov exponent, and others [3,7].…”