Using Machine Learning and Heart Rate Variability Features to Predict Epileptic Seizures

Abstract

[eng] This study constitutes a rst step towards a wearable epileptic seizure prediction device. We exploit the existing correlation between epileptic preictal states and heart rate variability features, since they can be measured by portable electrocardiogram recorders. By explicitly dealing with the intervals of extreme noise that may corrupt the electrocardiogram data during the seizures, our proposal is able to robustly train and use a Support Vector Machine to detect pre-ictal states. The experimental results show particularly good results in terms of positive and negative prediction. They also show the importance of a specic training for each patient.