Support vector machines for seizure detection in an animal model of chronic epilepsy

Nandan, Manu; Talathi, Sachin S.; Myers, Stephen M.; Ditto, William L.; Khargonekar, Pramod P.; Carney, Paul R.

doi:10.1088/1741-2560/7/3/036001

Cited by 47 publications

(24 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our case the most relevant are recent studies on PTZ-induced seizure onset detection in rats [38–40]. Actually, in previous works [30, 32] we had found a significant increase in tEEG power corresponding to seizure onset using population grand average power spectral density estimates and frequency band analysis.…”

Section: Introductionmentioning

confidence: 78%

Toward a Noninvasive Automatic Seizure Control System in Rats With Transcranial Focal Stimulations via Tripolar Concentric Ring Electrodes

Makeyev

Liu

Luna-Munguía

et al. 2012

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

Epilepsy affects approximately one percent of the world population. Antiepileptic drugs are ineffective in approximately 30% of patients and have side effects. We are developing a noninvasive, or minimally invasive, transcranial focal electrical stimulation system through our novel tripolar concentric ring electrodes to control seizures. In this study we demonstrate feasibility of an automatic seizure control system in rats with pentylenetetrazole-induced seizures through single and multiple stimulations. These stimulations are automatically triggered by a real-time electrographic seizure activity detector based on a disjunctive combination of detections from a cumulative sum algorithm and a generalized likelihood ratio test. An average seizure onset detection accuracy of 76.14% was obtained for the test set (n = 13). Detection of electrographic seizure activity was accomplished in advance of the early behavioral seizure activity in 76.92% of the cases. Automatically triggered stimulation significantly (p = 0.001) reduced the electrographic seizure activity power in the once stimulated group compared to controls in 70% of the cases. To the best of our knowledge this is the first closed-loop automatic seizure control system based on noninvasive electrical brain stimulation using tripolar concentric ring electrode electrographic seizure activity as feedback.

show abstract

Section: Introductionmentioning

confidence: 78%

Toward a Noninvasive Automatic Seizure Control System in Rats With Transcranial Focal Stimulations via Tripolar Concentric Ring Electrodes

Makeyev

Liu

Luna-Munguía

et al. 2012

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

show abstract

“…37 Some advantages of EEG are low cost, good examination speed, high time resolution, and noninvasiveness. [38][39][40][41] We used WT and ApEn for feature extraction. WT provides a useful spectral analysis to decompose several levels within the frequency domain, and at the same time preserved the time domain features.…”

Section: Discussionmentioning

confidence: 99%

High-Performance Seizure Detection System Using a Wavelet-Approximate Entropy-fSVM Cascade With Clinical Validation

et al. 2013

View full text Add to dashboard Cite

The classification of electroencephalography (EEG) signals is one of the most important methods for seizure detection. However, verification of an atypical epileptic seizure often can only be done through long-term EEG monitoring for 24 hours or longer. Hence, automatic EEG signal analysis for clinical screening is necessary for the diagnosis of epilepsy. We propose an EEG analysis system of seizure detection, based on a cascade of wavelet-approximate entropy for feature selection, Fisher scores for adaptive feature selection, and support vector machine for feature classification. Performance of the system was tested on open source data, and the overall accuracy reached 99.97%. We further tested the performance of the system on clinical EEG obtained from a clinical EEG laboratory and bedside EEG recordings. The results showed an overall accuracy of 98.73% for routine EEG, and 94.32% for bedside EEG, which verified the high performance and usefulness of such a cascade system for seizure detection. Also, the prediction model, trained by routine EEG, can be successfully generalized to bedside EEG of independent patients.

show abstract

“…A closed-loop system requires an efficient seizure detector to identify seizures at their onset and trigger an abortive stimulation before clinical manifestations occur. Although many seizure detection algorithms have so far been proposed [Nandan et al 2010;Polychronaki et al 2010;Zandi et al 2009], these have mainly been developed for high-speed desktop computers and short-term applications which cannot be employed in a low-power implantable microchip [Salam et al 2010c]. Further development in epileptic prosthetic devices would benefit from an epileptic seizure detection algorithm for low-power integrated circuits that could provide high-detection accuracy and reduce instrumentational lowfrequency noises [Patel et al 2009;Raghunathan et al 2009;Salam et al 2009Salam et al , 2010bVerma et al 2010].…”

Section: Introductionmentioning

confidence: 99%

Implantable Closed-Loop Epilepsy Prosthesis

Salam

Nguyen

2012

J. Emerg. Technol. Comput. Syst.

View full text Add to dashboard Cite

In this article, we present an implantable closed-loop epilepsy prosthesis, which is dedicated to automatically detect seizure onsets based on intracerebral electroencephalographic (icEEG) recordings from intracranial electrode contacts and provide an electrical stimulation feedback to the same contacts in order to disrupt these seizures. A novel epileptic seizure detector and a dedicated electrical stimulator were assembled together with common recording electrodes to complete the proposed prosthesis. The seizure detector was implemented in CMOS 0.18-μm by incorporating a new seizure detection algorithm that models timeamplitude and -frequency relationship in icEEG. The detector was validated offline on ten patients with refractory epilepsy and showed excellent performance for early detection of seizures. The electrical stimulator, used for suppressing the developing seizure, is composed of two biphasic channels and was assembled with embedded FPGA in a miniature PCB. The stimulator efficiency was evaluated on cadaveric animal brain tissue in an in vitro morphologic electrical model. Spatial characteristics of the voltage distribution in cortex were assessed in an attempt to identify optimal stimulation parameters required to affect the suspected epileptic focus. The experimental results suggest that lower frequency stimulation parameters cause significant amount of shunting of current through the cerebrospinal fluid; however higher frequency stimulation parameters produce effective spatial voltage distribution with lower stimulation charge.

show abstract

Support vector machines for seizure detection in an animal model of chronic epilepsy

Cited by 47 publications

References 29 publications

Toward a Noninvasive Automatic Seizure Control System in Rats With Transcranial Focal Stimulations via Tripolar Concentric Ring Electrodes

Toward a Noninvasive Automatic Seizure Control System in Rats With Transcranial Focal Stimulations via Tripolar Concentric Ring Electrodes

High-Performance Seizure Detection System Using a Wavelet-Approximate Entropy-fSVM Cascade With Clinical Validation

Implantable Closed-Loop Epilepsy Prosthesis

Contact Info

Product

Resources

About