Key result
The proposed hybrid feature extraction method achieved an accuracy of 85.30%, sensitivity of 59.93%, and specificity of 94.55% in classifying non-ictal versus ictal EEG signals on a combined dataset, outperforming existing methods.
Absolute Event Rate: 85.3% vs 72.7%
A novel hybrid feature extraction method improves the automated detection of epileptic seizures from single-channel EEG signals.
May aid automated single-channel EEG seizure detection; leaves open prospective validation before clinical use.
BACKGROUND: Epilepsy is a common chronic neurological disorder of the brain. Clinically, epileptic seizures are usually detected via the continuous monitoring of electroencephalogram (EEG) signals by experienced neurophysiologists. OBJECTIVE: In order to detect epileptic seizures automatically with a satisfactory precision, a new method is proposed which defines hybrid features that could characterize the epileptiform waves and classify single-channel EEG signals. METHODS: The hybrid features consist of both the ones usually used in EEG signal analysis and the Kraskov entropy based on Hilbert-Huang Transform which is proposed for the first time. With the hybrid features, EEG signals are classified and the epileptic seizures are detected. RESULTS: Three datasets are used for test on three binary-classification problems defined by clinical requirements for epileptic seizures detection. Experimental results show that the accuracy, sensitivity and specificity of the proposed methods outperform two state-of-the-art methods, especially on the databases containing signals from different sources. CONCLUSIONS: The proposed method provides a new avenue to assist neurophysiologists in diagnosing epileptic seizures automatically and accurately.
No takes yet. Share an insight, caveat, or question.
Lu et al. (2018) studied Epilepsy (n=33). Hybrid feature extraction (Kraskov entropy based on Hilbert-Huang Transform) with LS-SVM classifier vs. Existing state-of-the-art classification methods was evaluated on Classification accuracy for Non-Ictal versus Ictal EEG signals on a combined dataset (Data C). The proposed hybrid feature extraction method achieved an accuracy of 85.30%, sensitivity of 59.93%, and specificity of 94.55% in classifying non-ictal versus ictal EEG signals on a combined dataset, outperforming existing methods.
Synapse has enriched 4 closely related papers on similar clinical questions. Consider them for comparative context: