Early Seizure Detection Algorithm Based on Intracranial EEG and Random Forest Classification

The goal of this study is to provide a seizure detection algorithm that is relatively simple to implement on a microcontroller, so it can be used for an implantable closed loop stimulation device. We propose a set of 11 simple time domain and power bands features, computed from one intracranial EEG...

Full description

Saved in:
Bibliographic Details
Published inInternational journal of neural systems Vol. 25; no. 5; p. 1550023
Main Authors Donos, Cristian, Dümpelmann, Matthias, Schulze-Bonhage, Andreas
Format Journal Article
LanguageEnglish
Published Singapore 01.08.2015
Subjects
Adolescent
Adult
Algorithms
Brain - physiopathology
Brain - surgery
Early Diagnosis
Electrocorticography - methods
False Positive Reactions
Female
Humans
Implantable Neurostimulators
Male
Middle Aged
Seizures - diagnosis
Seizures - physiopathology
Seizures - surgery
Sensitivity and Specificity
Signal Processing, Computer-Assisted
Time Factors
Young Adult
EEG features
seizure detection
feature classification
Epilepsy
intracranial EEG
Online AccessGet more information
ISSN0129-0657
DOI10.1142/S0129065715500239

Cover

More Information
Summary:The goal of this study is to provide a seizure detection algorithm that is relatively simple to implement on a microcontroller, so it can be used for an implantable closed loop stimulation device. We propose a set of 11 simple time domain and power bands features, computed from one intracranial EEG contact located in the seizure onset zone. The classification of the features is performed using a random forest classifier. Depending on the training datasets and the optimization preferences, the performance of the algorithm were: 93.84% mean sensitivity (100% median sensitivity), 3.03 s mean (1.75 s median) detection delays and 0.33/h mean (0.07/h median) false detections per hour.
ISSN:0129-0657
DOI:10.1142/S0129065715500239