Patient-specific epilepsy seizure detection using random forest classification over one-dimension transformed EEG data

Abstract

This work presents a computational method for improving seizure detection for epilepsy diagnosis. Epilepsy is the second most common neurological disease. It impacts between 40 and 50 million of patients in the world. However, epilepsy diagnosis using electroen-cephalographic signals implies a long and expensive process involving medical specialists. The proposed system is a patient-specific system which performs an automatic detection of seizures from brainwaves applying a random forest classifier. Features are extracted using one-dimension reduced information from a spectro-temporal transformation of biosignals that pass through an envelope detector. The performance of the present method reached 97.12% of specificity, 99.29% of sensitivity, and a 0.77h−1 false positive rate. Therefore, the method hereby proposed has great potential for diagnosis support in clinical environments.