Prediction of epileptic seizures from EEG using analysis of ictal rules on Poincaré plane. (July 2017)

• Record Type: Journal Article
• Authors: Sharif, Babak; Jafari, Amir Homayoun
• Is Part Of: Computer methods and programs in biomedicine. Volume 145(2017)
• Page Start: 11
• Page End: 22
• Publication Date: 2017-07
• Subjects: Epileptic seizure prediction -- Poincaré plane -- Dynamic pattern -- Fuzzy rule; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2017.04.001
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: An innovative algorithm for feature extraction from time series is presented. A method for designing an optimum Poincaré Plane is presented that is able to transfer maximum information from time series to a sequence of Poincaré samples, while reducing the dimension of data. The dynamic of Poincaré samples are coded by dividing Poincaré plane to different areas. 64 Fuzzy rules are extracted from the coded sequence based on this dynamic coding which includes the nonlinear behavior of times series and is able to track ictal behaviors prior to seizure onset. Pre-Seizure indicators leading seizure prediction are detected based on the probability of defined rules. The rules that are more probable in ictal segments are defined as ictal rules. Predicting features are selected from ictal rules and these features are used as input to a SVM classifier to score the dynamic changes in order to predict seizures. Abstract: Background and Objective: Epilepsy is a neurological disorder that causes recurrent and abrupt seizures which makes the patients insecure. Predicting seizures can reduce the burdens of this disorder. Methods: A new approach in seizure prediction is presented that includes a novel technique in feature extraction from EEG. The algorithm firsts creates an embedding space from EEG time series. Then it takes samples with most of the information using an optimized and data specific Poincare plane. In order to quantify small dynamics on the Poincare plane, based on the order of locations of Poincaré samples in the sequence, 64 fuzzy rules in each channel are defined. Features are extracted based on the frequency distribution of these fuzzy rules in each minute. Then features with higher variance are selected as ictal features and again reduced using PCA. Finally, in order to evaluate how these innovative features can increase the performance of the seizure prediction algorithm, the transition from interictal to preictal state is scored utilizing SVM. Results: The algorithm is tested on 460 h of EEG from 19 patients of Freiburg dataset who had at least 3 seizures. Considering maximum Seizure Prediction Horizon of 42 minutes, average sensitivity was 91.8 - 96.6% and average false prediction rate was 0.05 - 0.08/h. Conclusions: The presented algorithm shows a better performance and more robustness compare to most of existing methods, and shows power in extracting optimal features from EEG.