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%.
|Revista Cubana de Ciencias Informáticas
|Published - Jan 2019
- multiway data analysis
- nonconvulsive epileptic seizures
- partial least squares