Dataset Information

Improved epileptic seizure detection combining dynamic feature normalization with EEG novelty detection.

ABSTRACT: Continuous electroencephalographic monitoring of critically ill patients is an established procedure in intensive care units. Seizure detection algorithms, such as support vector machines (SVM), play a prominent role in this procedure. To correct for inter-human differences in EEG characteristics, as well as for intra-human EEG variability over time, dynamic EEG feature normalization is essential. Recently, the median decaying memory (MDM) approach was determined to be the best method of normalization. MDM uses a sliding baseline buffer of EEG epochs to calculate feature normalization constants. However, while this method does include non-seizure EEG epochs, it also includes EEG activity that can have a detrimental effect on the normalization and subsequent seizure detection performance. In this study, EEG data that is to be incorporated into the baseline buffer are automatically selected based on a novelty detection algorithm (Novelty-MDM). Performance of an SVM-based seizure detection framework is evaluated in 17 long-term ICU registrations using the area under the sensitivity-specificity ROC curve. This evaluation compares three different EEG normalization methods, namely a fixed baseline buffer (FB), the median decaying memory (MDM) approach, and our novelty median decaying memory (Novelty-MDM) method. It is demonstrated that MDM did not improve overall performance compared to FB (p < 0.27), partly because seizure like episodes were included in the baseline. More importantly, Novelty-MDM significantly outperforms both FB (p = 0.015) and MDM (p = 0.0065).

SUBMITTER: Bogaarts JG

PROVIDER: S-EPMC5104774 | biostudies-literature | 2016 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Improved epileptic seizure detection combining dynamic feature normalization with EEG novelty detection.

Bogaarts J G JG Hilkman D M W DM Gommer E D ED van Kranen-Mastenbroek V H J M VH Reulen J P H JP

Medical & biological engineering & computing 20160406 12

Continuous electroencephalographic monitoring of critically ill patients is an established procedure in intensive care units. Seizure detection algorithms, such as support vector machines (SVM), play a prominent role in this procedure. To correct for inter-human differences in EEG characteristics, as well as for intra-human EEG variability over time, dynamic EEG feature normalization is essential. Recently, the median decaying memory (MDM) approach was determined to be the best method of normali ...[more]

PMID: 27053165

Similar Datasets

Project description:ObjectiveMarkers of seizure recurrence are needed to personalize antiseizure medication (ASM) therapy. In the clinical practice, EEG features are considered to be related to the risk of seizure recurrence for genetic generalized epilepsies (GGE). However, to our knowledge, there are no studies analyzing systematically specific EEG features as indices of ASM efficacy in GGE. In this study, we aimed at identifying EEG indicators of ASM responsiveness in Juvenile Myoclonic Epilepsy (JME), which, among GGE, is characterized by specific electroclinical features.MethodsWe compared the features of prolonged ambulatory EEG (paEEG, 22 h of recording) of JME patients experiencing seizure recurrence within a year ("cases") after EEG recording, with those of patients with sustained seizure freedom for at least 1 year after EEG ("controls"). We included only EEG recordings of patients who had maintained the same ASM regimen (dosage and type) throughout the whole time period from the EEG recording up to the outcome events (which was seizure recurrence for the "cases", or 1-year seizure freedom for "controls"). As predictors, we evaluated the total number, frequency, mean and maximum duration of epileptiform discharges (EDs) and spike density (i.e. total EDs duration/artifact-free EEG duration) recorded during the paEEG. The same indexes were assessed also in standard EEG (stEEG), including activation methods.ResultsBoth the maximum length and the mean duration of EDs recorded during paEEG significantly differed between cases and controls; when combined in a binary logistic regression model, the maximum length of EDs emerged as the only valid predictor. A cut-off of EDs duration of 2.68 seconds discriminated between cases and controls with a 100% specificity and a 93% sensitivity. The same indexes collected during stEEG lacked both specificity and sensitivity.SignificanceThe occurrence of prolonged EDs in EEG recording might represent an indicator of antiepileptic drug failure in JME patients.

Project description:Epilepsy is a common neurological disorder which affects 0.5-1% of the world population. Its diagnosis relies both on Electroencephalogram (EEG) findings and characteristic seizure-induced body movements--called seizure semiology. Thus, synchronous EEG and (2D)video recording systems (known as Video-EEG) are the most accurate tools for epilepsy diagnosis. Despite the establishment of several quantitative methods for EEG analysis, seizure semiology is still analyzed by visual inspection, based on epileptologists' subjective interpretation of the movements of interest (MOIs) that occur during recorded seizures. In this contribution, we present NeuroKinect, a low-cost, easy to setup and operate solution for a novel 3Dvideo-EEG system. It is based on a RGB-D sensor (Microsoft Kinect camera) and performs 24/7 monitoring of an Epilepsy Monitoring Unit (EMU) bed. It does not require the attachment of any reflectors or sensors to the patient's body and has a very low maintenance load. To evaluate its performance and usability, we mounted a state-of-the-art 6-camera motion-capture system and our low-cost solution over the same EMU bed. A comparative study of seizure-simulated MOIs showed an average correlation of the resulting 3D motion trajectories of 84.2%. Then, we used our system on the routine of an EMU and collected 9 different seizures where we could perform 3D kinematic analysis of 42 MOIs arising from the temporal (TLE) (n = 19) and extratemporal (ETE) brain regions (n = 23). The obtained results showed that movement displacement and movement extent discriminated both seizure MOI groups with statistically significant levels (mean = 0.15 m vs. 0.44 m, p<0.001; mean = 0.068 m(3) vs. 0.14 m(3), p<0.05, respectively). Furthermore, TLE MOIs were significantly shorter than ETE (mean = 23 seconds vs 35 seconds, p<0.01) and presented higher jerking levels (mean = 345 ms(-3) vs 172 ms(-3), p<0.05). Our newly implemented 3D approach is faster by 87.5% in extracting body motion trajectories when compared to a 2D frame by frame tracking procedure. We conclude that this new approach provides a more comfortable (both for patients and clinical professionals), simpler, faster and lower-cost procedure than previous approaches, therefore providing a reliable tool to quantitatively analyze MOI patterns of epileptic seizures in the routine of EMUs around the world. We hope this study encourages other EMUs to adopt similar approaches so that more quantitative information is used to improve epilepsy diagnosis.

Dataset Information

Improved epileptic seizure detection combining dynamic feature normalization with EEG novelty detection.

Publications

Improved epileptic seizure detection combining dynamic feature normalization with EEG novelty detection.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets