Automatic spike detection in EEG by a two-stage procedure based on support vector machines.

Nurettin Acir; Cüneyt Güzeliş

doi:10.1016/j.compbiomed.2003.08.003

Home/Archive/PubMed

PubMed · 15369708

Automatic spike detection in EEG by a two-stage procedure based on support vector machines.

Nurettin Acir·Cüneyt Güzeliş

View original source ↗Export metadata ↓

Abstract

In this study, we introduce a two-stage procedure based on support vector machines for the automatic detection of epileptic spikes in a multi-channel electroencephalographic signal. In the first stage, a modified non-linear digital filter is used as a pre-classifier to classify the peaks into two subgroups: (i) spikes and spike like non-spikes (ii) trivial non-spikes. The pre-classification done in the first stage not only reduces the computation time but also increases the overall detection performance of the procedure. In the second stage, the peaks falling into the first group are aimed to be separated from each other by a support vector machine that would function as a post-classifier. Visual evaluation, by two experts, of 19 channel EEG records of 7 epileptic patients showed that the best performance is obtained providing 90.3% sensitivity, 88.1% selectivity and 9.5% false detection rate.

Explore related subjects

Electroencephalography Epilepsy Humans Pattern Recognition, Automated Sensitivity and Specificity Signal Processing, Computer-Assisted Journal Article Research Support, Non-U.S. Gov't

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Nurettin Acir, Cüneyt Güzeliş. 2004. Automatic spike detection in EEG by a two-stage procedure based on support vector machines.. https://doi.org/10.1016/j.compbiomed.2003.08.003

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related citations

PubMed2006

Transcendental meditation may prevent partial epilepsy.

Explore the source record for details and available documents.

Electroencephalography↗

PubMed2006

A comparison of methods for ERP assessment in a P300-based GKT.

P300-based GKT (guilty knowledge test) has been suggested as an alternative approach for conventional polygraphy. The purpose of this study is to evaluate three classifying methods for this approach and compare their performances in a lab analogue. Several subjects went through the designed GKT paradigm and their respective brain signals were recorded. For the analysis of signals, BAD (bootstrapped amplitude difference) and BCD (bootstrapped correlation difference) methods as two predefined methods alongside a new approach consisting of wavelet features and a statistical classifier were implemented. The rates of correct detection in guilty and innocent subjects were 74-80%. The results indicate the potential of P300-based GKT for detecting concealed information, although further research is required to increase its accuracy and precision and evaluating its vulnerability to countermeasures.

Electroencephalography↗

PubMed2006

Pre-surgical evaluation and surgical treatment in children with extratemporal epilepsy.

INTRODUCTION: This review summarizes some patterns of pre-surgical evaluation and surgical treatment of extratemporal epilepsy in pediatric patients with medically refractory seizures, whose ictal behavior is variable. The most effective treatment for intractable partial epilepsy is a focal cortical resection with excision of the epileptogenic zone (the area of ictal onset and initial seizure propagation). This might be risky, though, in the case of a widespread lesion, sometimes encroaching one or more lobes, given the risk to the functional cerebral cortex. An anterior temporal lobectomy might prove more effective then in preventing seizures with fewer potential complications. If partial extratemporal epilepsy is associated with pharmaco-resistant seizures, the preoperative evaluation and operative strategy are determined according to the epileptogenic zone and to the relationship between a substrate-directed disorder and eloquent areas. The pediatric treatment of extratemporal epilepsy is aimed at controlling the seizures, avoiding morbidity, and improving the patient's quality of life through psychosocial integration. Since the immature brain is more plastic than when mature, the recovery of functions after surgery is greater in children than in adults. RECOMMENDATION: Early surgery is recommended for children with intractable epilepsy, and is now accepted as an important therapeutic modality also for children with chronic epilepsy. CONCLUSION: Technological advances in the last two decades, mainly in neuroimaging, have led many medical centers to consider surgical treatment of epilepsy, accuracy being granted by MRI-based neuronavigation systems-an interface between the lesion seen in the preoperative magnetic resonance imaging (MRI) and the operative field, often invisible to the surgeon.

Electroencephalography↗