A sparse Laguerre-Volterra autoregressive model for seizure prediction in temporal lobe epilepsy

Yu, Pen-Ning; Naiini, Shokofeh A.; Heck, Christi; Liu, Charles Y.; Song, Dong; Berger, Theodore W.

doi:10.1109/embc.2016.7591034

Cited by 8 publications

(3 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The drawback of this approach, on the other hand, is loss of the model's ability to capture dynamics at long time scales. To solve this system, we employ Laguerre basis functions in the Volterra series that results in a LVAR model [29][30][31][32]. In this approach, past input is first convolved with a set of Laguerre basis functions to include temporal dynamics.…”

Section: Lvar Modelmentioning

confidence: 99%

A sparse multiscale nonlinear autoregressive model for seizure prediction

Liu

Heck

et al. 2021

J. Neural Eng.

View full text Add to dashboard Cite

Objectives. Accurate seizure prediction is highly desirable for medical interventions such as responsive electrical stimulation. We aim to develop a classification model that can predict seizures by identifying preictal states, i.e. the precursor of a seizure, based on multi-channel intracranial electroencephalography (iEEG) signals. Approach. A two-level sparse multiscale classification model was developed to classify interictal and preictal states from iEEG data. In the first level, short time-scale linear dynamical features were extracted as autoregressive (AR) model coefficients; arbitrary (usually long) time-scale linear and nonlinear dynamical features were extracted as Laguerre–Volterra AR model coefficients; root-mean-square error of model prediction was used as a feature representing model unpredictability. In the second level, all features were fed into a sparse classifier to discriminate the iEEG data between interictal and preictal states. Main results. The two-level model can accurately classify seizure states using iEEG data recorded from ten canine and human subjects. Adding arbitrary (usually long) time-scale and nonlinear features significantly improves model performance compared with the conventional AR modeling approach. There is a high degree of variability in the types of features contributing to seizure prediction across different subjects. Significance. This study suggests that seizure generation may involve distinct linear/nonlinear dynamical processes caused by different underlying neurobiological mechanisms. It is necessary to build patient-specific classification models with a wide range of dynamical features.

show abstract

Section: Lvar Modelmentioning

confidence: 99%

A sparse multiscale nonlinear autoregressive model for seizure prediction

Liu

Heck

et al. 2021

J. Neural Eng.

View full text Add to dashboard Cite

show abstract

“…Works involving linear or nonlinear autoregressive models (AR/NAR), typical blackbox modeling tools, have been mostly proposed in the literature for seizure detection, prediction and synchronization [21][22][23][24][25], but approaches considering system identification have also been used to describe the so-called NAR fingerprints of patients [26,27]. However, the latter ones do not provide a systematic procedure to chacterize the AR equations in terms of dynamic models.…”

Section: Introductionmentioning

confidence: 99%

Epileptic seizure suppression: A computational approach for identification and control using real data

Brogin,

Faber,

Reyes-Garcia

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Epilepsy affects millions of people worldwide every year and remains an open subject for research. Current development on this field has focused on obtaining computational models to better understand its triggering mechanisms, attain realistic descriptions and study seizure suppression. Controllers have been successfully applied to mitigate epileptiform activity in dynamic models written in state-space notation, whose applicability is, however, restricted to signatures that are accurately described by them. Alternatively, autoregressive modeling (AR), a typical data-driven tool related to system identification (SI), can be directly applied to signals to generate more realistic models, and since it is inherently convertible into state-space representation, it can thus be used for the artificial reconstruction and attenuation of seizures as well. Considering this, the first objective of this work is to propose an SI approach using AR models to describe real epileptiform activity. The second objective is to provide a strategy for reconstructing and mitigating such activity artificially, considering non-hybrid and hybrid controllers − designed from ictal and interictal events, respectively. The results show that AR models of relatively low order represent epileptiform activities fairly well and both controllers are effective in attenuating the undesired activity while simultaneously driving the signal to an interictal condition. These findings may lead to customized models based on each signal, brain region or patient, from which it is possible to better define shape, frequency and duration of external stimuli that are necessary to attenuate seizures.

show abstract

“…Works involving linear or nonlinear autoregressive models (AR/NAR), typical black-box modeling tools, have been mostly proposed in the literature for seizure detection, prediction and synchronization [22][23][24][25][26], but approaches considering system January 6, 2023 2/32 identification have also been used to describe the so-called NAR fingerprints of patients [27,28]. However, the latter ones do not provide a systematic procedure to chacterize the AR equations in terms of dynamic models.…”

Section: Introductionmentioning

confidence: 99%

Epileptic seizure suppression: a computational approach for identification and control using real data

Brogin

Faber

Reyes-García

et al. 2023

Preprint

View full text Add to dashboard Cite

Epilepsy affects millions of people worldwide every year and remains an open subject for research. Current development on this field has focused on obtaining computational models to better understand its triggering mechanisms, attain realistic descriptions and study seizure suppression. Controllers have been successfully applied to mitigate epileptiform activity in dynamic models written in state-space notation, whose applicability is, however, restricted to signatures that are accurately described by them. Alternatively, autoregressive modeling (AR), a typical data-driven tool related to system identification (SI), can be directly applied to signals to generate more realistic models, and since it is inherently convertible into state-space, it can thus be used for the artificial reconstruction and attenuation of seizures as well. Considering this, the first objective of this work is to propose an SI approach using AR models to describe real epileptiform activity. The second objective is to provide a strategy for reconstructing and mitigating such activity artificially, considering non-hybrid and hybrid controllers – designed from ictal and interictal events, respectively. The results show that AR models of relatively low order represent epileptiform activities fairly well and both controllers are effective in attenuating the undesired activity while simultaneously driving the signal to an interictal stage. These findings may lead to customized models based on each signal, brain region or patient, from which it is possible to better define shape, frequency and duration of external stimuli that are necessary to attenuate seizures.

show abstract

A sparse Laguerre-Volterra autoregressive model for seizure prediction in temporal lobe epilepsy

Cited by 8 publications

References 8 publications

A sparse multiscale nonlinear autoregressive model for seizure prediction

A sparse multiscale nonlinear autoregressive model for seizure prediction

Epileptic seizure suppression: A computational approach for identification and control using real data

Epileptic seizure suppression: a computational approach for identification and control using real data

Contact Info

Product

Resources

About