Spatio-temporal patient–individual assessment of synchronization changes for epileptic seizure prediction

Winterhalder, Matthias; Schelter, Björn; Maiwald, Thomas; Brandt, Armin; Schad, Ariane; Schulze‐Bonhage, Andreas; Timmer, Jens

doi:10.1016/j.clinph.2006.07.312

Cited by 94 publications

(59 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Signal analysis and its trajectory in the phase space can lead to a better understanding of the system's dynamics and provide valuable information about attractors and system behavior. In particular, nonlinear time series analysis methods are presented to identify epileptic seizure states 16,[21][22][23][24][25][26] . To a certain extent, these methods mainly include the Lyapunov exponent and the correlation dimension, which is able to extract the properties of the useful EEG data to provide evidence to confirm the existence of a previous state of seizure in temporal lobe epilepsy [22][23][24][25] .…”

Section: Feature Extractionmentioning

confidence: 99%

Detection and Prediction of Absence Seizures Based on Nonlinear Analysis of the EEG in Wag/Rij Animal Model

Lashkari

Sheikhani

Golpayegani

et al. 2018

Int Clin Neurosci J

View full text Add to dashboard Cite

Background: Epilepsy is a common neurological disorder with a prevalence of 1% of the world population. Absence epilepsy is a form of generalized seizures with Spike wave discharge in EEG. Epileptic patients have frequent absence seizures that cause immediate loss of consciousness. Methods: In this study, it has been tried to explore whether EEG changes can effectively detect epilepsy in animal model applying non-linear features. To predict the occurrence of absence epilepsy, a long-term EEG signal has been recorded from frontal cortex in seven Wag/Rij rats. After preprocessing, the data was transferred to the phase space to extract the brain system dynamic and geometric properties of this space. Finally, the ability of each features to predict and detect absence epilepsy with two criteria of predictive time and the accuracy of detection and its results were compared with previous studies. Results:The results indicate that the brain system dynamic changes during the transition from freeseizure to pre-seizure and then seizure. Proposed approach diagnostic characteristics yielded 97% accuracy of absence epilepsy diagnosis indicating that due to the nonlinear and complex nature of the system and the brain signal, the use of methods consistent with this nature is important in understanding the dynamic transfer between different epileptic seizures. Conclusion: By changing the state of the absence Seizures, the dynamics are changing, and the results of this research can be useful in real-time applications such as predicting epileptic seizures.

show abstract

Section: Feature Extractionmentioning

confidence: 99%

Detection and Prediction of Absence Seizures Based on Nonlinear Analysis of the EEG in Wag/Rij Animal Model

Lashkari

Sheikhani

Golpayegani

et al. 2018

Int Clin Neurosci J

View full text Add to dashboard Cite

show abstract

“…For the interictal data set, each 1-hour record was tested using a classifier trained from all the 30-minute preseizure data (class 1), as well as all the other 1-hour records of interictal data (class 2). False positives were scored using a 30 minute Seizure Occurrence Period [7].…”

Section: Machine Learningmentioning

confidence: 99%

“…Our seizure prediction algorithm is evaluated on the Freiburg EEG database, which contains the ECoG recordings from 21 epileptic seizure patients undergoing invasive pre-surgical epilepsy monitoring at the Epilepsy Center of the University Hospital of Freiburg, Germany [4], [7]. The data consist of six channels (i.e., recordings from 6 different electrodes), sampled at 256 Hz.…”

Section: Freiburg Data Setmentioning

confidence: 99%

Epileptic seizure prediction using the spatiotemporal correlation structure of intracranial EEG

Williamson

Bliss

Browne

2011

2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

View full text Add to dashboard Cite

A patient-specific seizure prediction algorithm is proposed that extracts novel multivariate signal coherence features from ECoG recordings and classifies a patient's pre-seizure state. The algorithm uses space-delay correlation and covariance matrices at several delay scales to extract the spatiotemporal correlation structure from multichannel ECoG signals. Eigenspectra and amplitude features are extracted from the correlation and covariance matrices, followed by dimensionality reduction using principal components analysis, classification using a support vector machine, and temporal integration to produce a seizure prediction score. Evaluation on the Freiburg EEG database produced a sensitivity of 90.8% and false positive rate of .094.

show abstract

“…Phase coherence, joint with another synchronization measure, lag synchronization, was also discussed in [42], where the issue of the variability between patients was raised. Phase synchronization methods remain among the most successfully applied [43].…”

Section: Seizure Prediction and Detectionmentioning

confidence: 99%

Mapping the epileptic brain with EEG dynamical connectivity: Established methods and novel approaches

et al. 2012

View full text Add to dashboard Cite

Several algorithms rooted in statistical physics, mathematics and machine learning are used to analyze neuroimaging data from patients affected by epilepsy, with the main goals of localizing the brain region where seizure originates from and of detecting upcoming seizure activity in order to trigger therapeutic neurostimulation devices. Some of these methods explore the dynamical connections between brain regions, exploiting the high temporal resolution of the electroencephalographic signals recorded at the scalp or directly from the cortical surface or in deeper brain areas. In this paper we describe this specific class of algorithms and their clinical application, by reviewing the state of the art and reporting their application on EEG data from an epileptic patient.

show abstract

Spatio-temporal patient–individual assessment of synchronization changes for epileptic seizure prediction

Cited by 94 publications

References 47 publications

Detection and Prediction of Absence Seizures Based on Nonlinear Analysis of the EEG in Wag/Rij Animal Model

Detection and Prediction of Absence Seizures Based on Nonlinear Analysis of the EEG in Wag/Rij Animal Model

Epileptic seizure prediction using the spatiotemporal correlation structure of intracranial EEG

Mapping the epileptic brain with EEG dynamical connectivity: Established methods and novel approaches

Contact Info

Product

Resources

About