Using Electrocardiogram Signal Features and Heart Rate Variability to Predict Epileptic Attacks

Since the increase in neuronal activity during an epileptic attack affects the voluntary nervous system, and the voluntary nervous system also affects the heart rate variability, it can be concluded that seizures can be predicted by monitoring heart rate variability. In this study, a new method for predicting epilepsy through the analysis of heart rate variability is proposed. In the proposed method, 12 features are extracted from the heart rate variability signal in time, frequency, time-frequency, and nonlinear domains to predict epileptic seizures. We used a multivariate statistical process control algorithm for abnormality detection. The presented algorithm was evaluated on a dataset consisting of 17 patients, where the obtained results show that the proposed method can predict epileptic attacks with an accuracy of 88.2%. From a practical point of view, due to the ease of obtaining the heart rate variability signal, the proposed algorithm is more promising than the algorithms that use brain signal processing to predict epilepsy.