Using Partial Least Squares for Nonconvulsive Epileptic Seizure Detection

Nonconvulsive status epilepticus (NCSE) is a condition where the patient is exposed to abnormally prolonged nonconvulsive epileptic seizures (NCES)(epileptic seizures without evident physical symptoms). Hence, the diagnosis can only be stated by means of EEG monitoring. NCSE and NCES are associated with severe irreversible brain damage and poor outcome. Hence, the prompt recognition of patients at risk of suffering NCSE is necessary in order to manage them properly and to prevent further brain injury. However, despite the clinical efforts to manage NCES and NCSE, and improve the patient’s outcome, monitoring this pathology in real-time is very difficult. In a previous work of these authors, a patient specific method is proposed to detect the NCES. This method identifies the NCES by exploiting the similarity between the first NCES detected by the physician on the EEG and the rest of NCES in the recording. The method used a support vector machine classifier to perform the classification, obtaining specificity, and sensitivity, results over 98%. However, the method was vulnerable to missclassify epochs with EEG patterns resembling a NCES. In this paper, we propose a complementary method based in partial least squares (PLS) to improve the identification of the NCES patterns of the previously proposed method in dubious EEG segments. The proposed method improved the SVM based model performance obtaining specificity ans sensitivity values over 99%