Dynamic Training of a Novelty Classifier Algorithm for Real-Time Early Seizure Onset Detection

AbstractThe objective of this study was to develop an adaptive framework for seizure detection in real-time that is practical to use in the Epilepsy Monitoring Unit (EMU) as a warning signal, and whose output helps characterize epileptiform activity. Our framework uses a one-class Support Vector Machine (SVM) that is being trained dynamically according to past activity in all available channels. This is done to evaluate the novelty of the current instance according to previous activity. Our algorithm was tested on intracranial EEG from human epilepsy patients that are admitted to the EMU for presurgical evaluation. In this study, we compared multiple configurations for using a one-class SVM to assess if there is significance over specific neural features or electrode locations. Our results show our algorithm is capable of running in real-time and achieving a high performance for early seizure-onset detection with a low false-positive rate and robustness to different types of seizure-onset patterns as well as to the number of channels used. This algorithm offers a solution to warning systems in the EMU as well as a tool for seizure characterization during post-hoc analysis of intracranial EEG data for surgical resection of the epileptogenic network.HighlightsThis study proposes a dynamic training algorithm that efficiently detects sudden novel changes in intracranial electroencephalographic activity, creating a reliable seizure onset detection algorithm that does not need prior training.The algorithm described has the capability to be implemented in real-time, independently of the number of channels that are being analyzed.The presented detector shows high performance and reliability to be easily implemented in the Epilepsy Monitoring Unit to quickly alert clinical staff of seizure events.

Download Full-text

One Dimensional Convolutional Neural Networks for Seizure Onset Detection Using Long-term Scalp and Intracranial EEG

Neurocomputing ◽

10.1016/j.neucom.2021.06.048 ◽

2021 ◽

Author(s):

Xiaoshuang Wang ◽

Xiulin Wang ◽

Wenya Liu ◽

Zheng Chang ◽

Tommi Karkkainen ◽

...

Keyword(s):

Neural Networks ◽

Convolutional Neural Networks ◽

Onset Detection ◽

Seizure Onset ◽

Intracranial Eeg ◽

One Dimensional

Download Full-text

An algorithm for seizure onset detection using intracranial EEG

Epilepsy & Behavior ◽

10.1016/j.yebeh.2011.08.031 ◽

2011 ◽

Vol 22 ◽

pp. S29-S35 ◽

Cited By ~ 38

Author(s):

Alaa Kharbouch ◽

Ali Shoeb ◽

John Guttag ◽

Sydney S. Cash

Keyword(s):

Onset Detection ◽

Seizure Onset ◽

Intracranial Eeg

Download Full-text

Prolonged postictal hemianopsia after a focal extraoccipital onset seizure

BMJ Case Reports ◽

10.1136/bcr-2020-239021 ◽

2021 ◽

Vol 14 (1) ◽

pp. e239021

Author(s):

Vibhangini S Wasade ◽

Jennifer L Logan

Keyword(s):

Epileptiform Activity ◽

Diagnostic Evaluation ◽

Onset Seizure ◽

Seizure Onset ◽

Seizure Termination ◽

Seizure Onset Zone ◽

History Of ◽

Epilepsy Monitoring

We report a case of a prolonged postictal hemianopsia occurring after a focal extraoccipital seizure. A 55-year-old man with a history of neurosyphilis, treated with penicillin, presented to our epilepsy monitoring unit (EMU) for diagnostic evaluation of his spells occurring for 2 years. The spell semiology was stereotypical, described as oral and manual automatisms, speech difficulty and unresponsiveness. During the EMU stay, after his typical seizure was recorded, he experienced right hemianopsia lasting for 2 hours. Electrographically, the ictal pattern was prominent over the left temporal derivation and propagated to the left occipital derivation as the seizure progressed. Interictal epileptiform activity was over the left temporal derivations. We support the view that postictal phenomenon may represent merely a seizure termination zone and not be necessarily localising to the seizure onset zone. Furthermore, prolonged isolated postictal symptom of hemianopsia could also be noted in rare situations.

Download Full-text

An Approach to Seizure Onset Detection Using Fuzzy Logic Based on Seizure Evolution in Intracranial EEG

Journal of Medical Devices ◽

10.1115/1.3591388 ◽

2011 ◽

Vol 5 (2) ◽

Cited By ~ 1

Author(s):

Ahmed Rabbi ◽

Reza Fazel-Rezai

Keyword(s):

Fuzzy Logic ◽

Onset Detection ◽

Seizure Onset ◽

Intracranial Eeg

Download Full-text

Automated seizure onset detection for accurate onset time determination in intracranial EEG

Clinical Neurophysiology ◽

10.1016/j.clinph.2008.08.025 ◽

2008 ◽

Vol 119 (12) ◽

pp. 2687-2696 ◽

Cited By ~ 38

Author(s):

Alexander M. Chan ◽

Felice T. Sun ◽

Erem H. Boto ◽

Brett M. Wingeier

Keyword(s):

Onset Time ◽

Onset Detection ◽

Seizure Onset ◽

Intracranial Eeg ◽

Time Determination

Download Full-text

Corrigendum to “An algorithm for seizure onset detection using intracranial EEG” [Epilepsy & Behavior 22, Issue S1 (2011) S29-S35]

Epilepsy & Behavior ◽

10.1016/j.yebeh.2012.04.118 ◽

2012 ◽

Vol 24 (3) ◽

pp. 389 ◽

Cited By ~ 3

Author(s):

Alaa Kharbouch ◽

Ali Shoeb ◽

John Guttag ◽

Sydney S. Cash

Keyword(s):

Onset Detection ◽

Seizure Onset ◽

Intracranial Eeg

Download Full-text

A Fuzzy Logic System for Seizure Onset Detection in Intracranial EEG

Computational Intelligence and Neuroscience ◽

10.1155/2012/705140 ◽

2012 ◽

Vol 2012 ◽

pp. 1-12 ◽

Cited By ~ 38

Author(s):

Ahmed Fazle Rabbi ◽

Reza Fazel-Rezai

Keyword(s):

Fuzzy Rule ◽

Epileptogenic Zone ◽

Onset Detection ◽

Seizure Onset ◽

Intracranial Eeg ◽

Fuzzy Algorithms ◽

Remote Zone ◽

Threshold Procedure ◽

Eeg Recordings ◽

Logic System

We present a multistage fuzzy rule-based algorithm for epileptic seizure onset detection. Amplitude, frequency, and entropy-based features were extracted from intracranial electroencephalogram (iEEG) recordings and considered as the inputs for a fuzzy system. These features extracted from multichannel iEEG signals were combined using fuzzy algorithms both in feature domain and in spatial domain. Fuzzy rules were derived based on experts' knowledge and reasoning. An adaptive fuzzy subsystem was used for combining characteristics features extracted from iEEG. For the spatial combination, three channels from epileptogenic zone and one from remote zone were considered into another fuzzy subsystem. Finally, a threshold procedure was applied to the fuzzy output derived from the final fuzzy subsystem. The method was evaluated on iEEG datasets selected from Freiburg Seizure Prediction EEG (FSPEEG) database. A total of 112.45 hours of intracranial EEG recordings was selected from 20 patients having 56 seizures was used for the system performance evaluation. The overall sensitivity of 95.8% with false detection rate of 0.26 per hour and average detection latency of 15.8 seconds was achieved.

Download Full-text

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

International Journal of Neural Systems ◽

10.1142/s0129065715500239 ◽

2015 ◽

Vol 25 (05) ◽

pp. 1550023 ◽

Cited By ~ 70

Author(s):

Cristian Donos ◽

Matthias Dümpelmann ◽

Andreas Schulze-Bonhage

Keyword(s):

Random Forest ◽

Seizure Detection ◽

Detection Algorithm ◽

Seizure Onset ◽

Intracranial Eeg ◽

Random Forest Classification ◽

Forest Classification ◽

Seizure Onset Zone ◽

Early Seizure

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.

Download Full-text