Epileptic Seizure Prediction

Epilepsy cannot be successfully treated through medications or resection in about 30% of patients. Furthermore, an estimated 0.1 percent of epileptic patients suffer sudden deaths resulting from injuries sustained during seizures. For this reason, patients with intractable seizures need alternative therapeutic approaches. An engineered device tailored toward seizure prediction that warns patients of an impending seizure or that intervenes to prevent its occurrence may significantly decrease the burden of epilepsy. Although much research efforts have been directed at the development of a seizure prediction algorithm, a therapeutic or warning device that meets stringent clinical requirements is still elusive. In the present study a novel patient-specific seizure prediction method is proposed. The method is based on time-frequency analysis of scalp electroencephalogram (sEEG) and the use of state-of-the-art unsupervised feature representation learning techniques: reconstruction independent component analysis and sparse filtering. In a moving window analysis, a novel engineered bivariate EEG characterizing measure named Normalized Logarithmic Wavelet Packet Coefficient Energy Ratios (NLWPCER) was extracted from all possible combination of EEG channels and relevant frequency sub-bands. Thereafter unsupervised representation learning algorithm adapted to each patient through Bayesian optimization procedure was used to learn NLWPCER features representation or transformation suitable for data classification task. Two classification models: Artificial Neural Network (ANN) and Support Vector Machine (SVM) were developed and trained to learn preictal (pre-seizure) and interictal (normal) EEG feature vector patterns. The output of the classifiers was regularized through a post processing operation aimed at reducing false prediction rate (FPR) and making decision on the generation of prediction alarms. The proposed method was evaluated using approximately 545 h CHB-MIT scalp EEG recording of 17 patients with a total of 43 leading seizures. On the average, with SVM classifier the proposed seizure prediction algorithm achieved a sensitivity of 87.26% and false prediction rate of 0.08h-1 while with ANN classifier the algorithm achieved average sensitivity and false prediction rate of 75.49% and 0.13h-1 respectively. The proposed method was validated using an Analytic Random Predictor (ARP). The results obtained in this work opens a pathway for a robust and consistent real-time portable seizure prediction device suitable for clinical applications.

Quantitative Neuroscience, 2004

Several methods have been suggested to predict the onset of epileptic seizures from EEG data. We evaluated the performance of three predictions methods: the "dynamical similarity index", the "effective correlation dimension" and an extended, prospective version of the "accumulated energy". These prediction methods were applied on a large pool of intracranial EEG data from 21 patients. Altogether, 582 hours EEG data and 88 seizures were investigated.

2013

Approximately 50 million people worldwide suffer from epilepsy. Although 70% can control their seizures by anti-epileptic drugs, it is still a cumbersome disease to live with for a large group of patients. The current PhD dissertation investigates how these people can be helped by continous monitoring of their brain waves. More specifically, three issues were investigated: The feasibility of automatic seizure prediction, optimization of automatic seizure detection algorithms, and the link between intraand extracranial EEG. Regarding feasibility of automatic seizure prediction, neither the author nor any other in the seizure prediction society have yet obtained clinical applicable prediction results. However, this should not be taken as discouraging for the future. New large public databases have emerged during 2012 which might provide the means to identify patterns leading to reliable seizure prediction algorithms. More promising results were obtained in the investigating of possibl...

Springer Optimization and Its Applications, 2007

Objective: Epilepsy, one of the most common neurological disorders, constitutes a unique opportunity to study the dynamics of spatiotemporal state transitions in real, complex, nonlinear dynamical systems. In this study, we evaluate the performance of a prospective on-line real-time seizure prediction algorithm in two patients from a common database.

Epilepsy is a common neurological disorders characterized by sudden recurrent seizures. Electroencephalogram (EEG) is widely used to diagnose possible epileptic seizure. Many research works have been devoted to predict epileptic seizure by analyzing EEG signal. Seizure prediction by analyzing EEG signals are challenging task due to variations of brain signals of different patients. In this paper, we propose a new approach for feature extraction based on phase correlation in EEG signals. In phase correlation, we calculate relative change between two consecutive segments of an EEG signal and then combine the changes with neighboring signals to extract features. These features are then used to classify preictal/ictal and interictal EEG signals for seizure prediction. Experiment results show that the proposed method carries good prediction rate with greater consistence for the benchmark data set in different brain locations compared to the existing state-of-the-art methods.

Journal of Pharmacy and Pharmaceutical Sciences

Clinical data is complex, context-dependent, and multi-dimensional, and such data generates an amalgamation of computing research challenges. To extract and interpret the useful information from raw data is a challenging job. This study aims at developing an automated predictive model to diagnose the state of an epileptic patient using EEG signals. The segmented EEG signals are utilized to extract various statistical features which are used for prediction. Strategically, we have designed a fully automated neural network model, capable of classifying the seizure activity into ictal, interictal and normal state with an accuracy as high as 99.3%, maximum sensitivity of 100% and specificity as high as 98.3% for all the classes. For the different set of parameters and optimum number of neurons in hidden layer, ANN model revealed a superior model for validating the classification.

Patients suffering from epileptic seizures are usually treated with medication and/or surgical procedures. However, in more than 30% of cases, medication or surgery does not effectively control seizure activity. A method that predicts the onset of a seizure before it occurs may prove useful as patients might be alerted to make themselves safe or seizures could be prevented with therapeutic interventions just before they occur. Abnormal neuronal activity, the preictal state, starts a few minutes before the onset of a seizure. In recent years, different methods have been proposed to predict the start of the preictal state. These studies follow some common steps, including recording of EEG signals, preprocessing, feature extraction, classification, and postprocessing. However, online prediction of epileptic seizures remains a challenge as all these steps need further refinement to achieve high sensitivity and low false positive rate. In this paper, we present a comparison of state-of-the-art methods used to predict seizures using both scalp and intracranial EEG signals and suggest improvements to existing methods.

2015 Signal Processing Symposium (SPSympo), 2015

h i g h l i g h t s g r a p h i c a l a b s t r a c t • Multivariate statistical process control (MSPC) can be used for seizure prediction using EEG signal. • 98% to less than 99% of variation of interictal data should be retained in the PCA model to predict seizures. • Less computational time because of temporal-based feature and MSPC.

Physica D: Nonlinear Phenomena, 2004

Epilepsy is characterized by the spontaneous and unforeseeable occurrence of seizures, during which the perception or behavior of patients is disturbed. The predictability of these seizures would render novel therapeutic approaches possible. Several prediction methods have claimed to be able to predict seizures based on EEG recordings minutes in advance. However, the term seizure prediction is not unequivocally defined, different criteria to assess prediction methods exist, and only little attention has been paid to issues of sensitivity and false prediction rate. We introduce an assessment criterion called the seizure prediction characteristic that incorporates the assessment of sensitivity and false prediction rate. Within this framework, three nonlinear seizure prediction methods were evaluated on a large EEG data pool of 21 patients. Altogether, 582 h intracranial EEG data and 88 seizures were examined. With a rate of 1-3.6 false predictions per day, the "dynamical similarity index" achieves a sensitivity between 21 and 42%, which was the best result of the three methods. Sensitivity was between 18 and 31% for the extended, prospective version of the "accumulated energy" and between 13 and 30% for the "effective correlation dimension". These results still are not sufficient for clinical applications.

Biomedical & Pharmacology Journal, 2014

Epilepsy is a common neurological disorder affecting more than 1.5 percent worldwide. Twenty percent of epilepsies are drug resistant. Therefore, early detection of prediction of epileptic seizures is of prime significance to decrease the burdens of the disease. There is strong evidence indicating seizures develop minutes to hours before clinical onset. This change is based on quantitative studies of long term electroencephalographic monitoring (EEG) from patients administered for epilepsy surgery. The possibility of early prediction of seizure has drawn the research interest of diverse fields in medical, engineering, and patent publications. Techniques used to predict seizures include frequency-based methods, statistical analysis of EEG signals, non-linear dynamics (chaos), and intelligent expert systems. Developing efficient methods to predict seizures can lead to designing novel diagnostic and therapeutic techniques for the early diagnosis of seizure attack or preventing the attacks through appropriate modulations of brain activities. The present study reviews the most important and recent methods for seizure prediction. In line with introduction of different efficient seizure predicting approaches, great research interest has been focused on developing new modalities that incorporate these approaches to predict early onset of seizures minutes to hours before they initiate. These modalities will enable experts to develop new interventional treatments such as appropriate responsive electric stimulation applied immediately after the prediction to prevent the seizures or modulating stimulation in controlling the seizure attacks. In the near future, seizures can be predicted in time and prevented before clinical and physical indications.