Patient-specific epileptic seizure detection in long-term EEG recording in paediatric patients with intractable seizures

• Published in: IET Intelligent Signal Processing Conference 2013 (ISP 2013) p. 7.P06
• Main Authors: Zabihi, M, Kiranyaz, S, Ince, T, Gabbouj, M
• Format: Conference Proceeding
• Language: English
• Published: Stevenage, UK IET 2013
• Subjects: Bioelectric signals; Electrical activity in neurophysiological processes; Electrodiagnostics and other electrical measurement techniques; Patient diagnostic methods and instrumentation; Signal processing and detection; linear kernel; electroencephalography; time domain; support vector machines; long term EEG recording; feature selection method; patient specific epileptic seizure detection; noninvasive EEG signal analysis; signal classification; paediatric patients; intractable seizures; medical signal processing; time frequency domain; support vector machine; conditional mutual information maximization; EEG data; patient diagnosis; composite feature vector; nonlinear feature sets
• ISBN: 1849197741; 9781849197748
• DOI: 10.1049/cp.2013.2060

The contemporary diagnosis of epileptic seizures is dominated by non-invasive EEG signal analysis and classification. In this paper, we propose a patient-specific seizure detection technique, which selects the optimal feature subsets and trains a dedicated classifier for each patient in order to maximize the classification performance. Our method exploits time domain, frequency domain, time-frequency domain and non-linear feature sets. Then, by using Conditional Mutual Information Maximization (CMIM) as the feature selection method the optimal feature subset is chosen over which the Support Vector Machine is trained as the classifier. In this study, both train and test sets contain 50% of seizure and non-seizure segments of the EEG signal. From the CHB-MIT Scalp benchmark EEG dataset, we used the EEG data from four subjects with overall 21 hours of recording. Support Vector Machine (SVM) with linear kernel is used as the classifier. The experimental results show a delicate classification performance over the test set: i.e., an average of 90.62% sensitivity and 99.32% specificity are acquired when all channels and recordings are used to form a composite feature vector. In addition, an average of 93.78% sensitivity and a specificity of 99.05% are obtained using CMIM.