Early Seizure Detection by Applying Frequency-Based Algorithm Derived from the Principal Component Analysis.

The use of automatic electrical stimulation in response to early seizure detection has been introduced as a new treatment for intractable epilepsy. For the effective application of this method as a successful treatment, improving the accuracy of the early seizure detection is crucial. In this paper, we proposed the application of a frequency-based algorithm derived from principal component analysis (PCA), and demonstrated improved efficacy for early seizure detection in a pilocarpine-induced epilepsy rat model. A total of 100 ictal electroencephalographs (EEG) during spontaneous recurrent seizures from 11 epileptic rats were finally included for the analysis. PCA was applied to the covariance matrix of a conventional EEG frequency band signal. Two PCA results were compared: one from the initial segment of seizures (5 sec of seizure onset) and the other from the whole segment of seizures. In order to compare the accuracy, we obtained the specific threshold satisfying the target performance from the training set, and compared the False Positive (FP), False Negative (FN), and Latency (Lat) of the PCA based feature derived from the initial segment of seizures to the other six features in the testing set. The PCA based feature derived from the initial segment of seizures performed significantly better than other features with a 1.40% FP, zero FN, and 0.14 s Lat. These results demonstrated that the proposed frequency-based feature from PCA that captures the characteristics of the initial phase of seizure was effective for early detection of seizures. Experiments with rat ictal EEGs showed an improved early seizure detection rate with PCA applied to the covariance of the initial 5 s segment of visual seizure onset instead of using the whole seizure segment or other conventional frequency bands.