PubMed Health⌕ Search
Home/Archive/PubMed

PubMed · 16122807

Automatic detection of interictal spikes using data mining models.

Pablo Valenti·Enrique Cazamajou·Marcelo Scarpettini·Ariel Aizemberg·Walter Silva·Silvia Kochen
View original source ↗Export metadata ↓

Abstract

A prospective candidate for epilepsy surgery is studied both the ictal and interictal spikes (IS) to determine the localization of the epileptogenic zone. In this work, data mining (DM) classification techniques were utilized to build an automatic detection model. The selected DM algorithms are: Decision Trees (J 4.8), and Statistical Bayesian Classifier (naïve model). The main objective was the detection of IS, isolating them from the EEG's base activity. On the other hand, DM has an attractive advantage in such applications, in that the recognition of epileptic discharges does not need a clear definition of spike morphology. Furthermore, previously 'unseen' patterns could be recognized by the DM with proper 'training'. The results obtained showed that the efficacy of the selected DM algorithms is comparable to the current visual analysis used by the experts. Moreover, DM is faster than the time required for the visual analysis of the EEG. So this tool can assist the experts by facilitating the analysis of a patient's information, and reducing the time and effort required in the process.

Explore related subjects

Action PotentialsAlgorithmsBayes TheoremDecision TreesElectroencephalographyEpilepsyHumansModels, NeurologicalPreoperative CareJournal Article

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Pablo Valenti, Enrique Cazamajou, Marcelo Scarpettini, Ariel Aizemberg, Walter Silva, Silvia Kochen. 2005-08-24. Automatic detection of interictal spikes using data mining models.. https://doi.org/10.1016/j.jneumeth.2005.06.005

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

KEEP EXPLORING

Related citations

PubMed2006

Differential expression of voltage-activated calcium currents in zebrafish retinal ganglion cells.

We report a study on the characterization of voltage-activated calcium currents (I(Ca)) in retinal ganglion cells (RGCs) and the topographic distribution of RGCs that express different types of I(Ca) in zebrafish retinas. In acutely isolated zebrafish RGCs, both high-voltage-activated (HVA; peak activation potential +7.4 +/- 1.1 mV) and low-voltage-activated (LVA; peak activation potential -33.0 +/- 1.2 mV) I(Ca) were recorded. HVA I(Ca) were recorded in all of the tested RGCs, whereas LVA I(Ca) were recorded in approximately one-third of the tested cells. In RGCs that expressed both HVA and LVA I(Ca), the two currents were readily separated by depolarizing the cell membrane to different voltages from different holding potentials. Among RGCs that expressed LVA I(Ca), some cells expressed large LVA I(Ca) (up to 130 pA), whereas others expressed small LVA I(Ca) (approximately 20 pA). RGCs that expressed large and small LVA I(Ca) were designated as class I and class II cells, respectively, and RGCs that expressed only HVA I(Ca) were designated as class III cells. The topographic distribution of cell classes was similar in various areas of the retina. In the nasal-ventral retina, for example, class III cells outnumbered class I and class II cells by 10.8- and 2.6-fold, respectively. In the temporal and dorsal retinas, the density of class III cells slightly decreased, whereas the density of class I and class II cells increased. The differential expression of I(Ca) in RGCs may correlate with the development and function of the retina.

Action Potentials↗
PubMed2006

Zonal organization of the mouse flocculus: physiology, input, and output.

The zones of the flocculus have been mapped in many species with a noticeable exception, the mouse. Here, the functional map of the mouse was constructed via extracellular recordings followed by tracer injections of biotinylated-dextran-amine and immunohistochemistry for heat-shock protein-25. Zones were identified based on the Purkinje cell complex spike modulation occurring in response to optokinetic stimulation. In zones 1 and 3 Purkinje cells responded best to rotation about a horizontal axis oriented at 135 degrees ipsilateral azimuth, whereas in zones 2 and 4 they responded best to rotation about the vertical axis. The tracing experiments showed that Purkinje cells of zone 1 projected to the parvicellular part of lateral cerebellar nucleus and superior vestibular nucleus, while Purkinje cells of zone 3 projected to group Y and the superior vestibular nucleus. Purkinje cells of zones 2 and 4 projected to the magnocellular and parvicellular parts of the medial vestibular nucleus, while some also innervated the lateral vestibular nucleus or nucleus prepositus hypoglossi. The climbing fiber inputs to Purkinje cells in zones 1 and 3 were derived from neurons in the ventrolateral outgrowth of the contralateral inferior olive, whereas those in zones 2 and 4 were derived from the contralateral caudal dorsal cap. Purkinje cells in zones 1 and 2, but not in zones 3 and 4, were positively labeled for heat-shock protein-25. The present study illustrates that Purkinje cells in the murine flocculus are organized in discrete zones with specific functions, specific input - output relations, and a specific histochemical signature.

Action Potentials↗
PubMed2006

Bootstrap-based methods for testing factor-by-curve interactions in generalized additive models: assessing prefrontal cortex neural activity related to decision-making.

In many situations the effect of a continuous covariate on response varies across groups defined by levels of a categorical variable. This paper addresses generalized additive models incorporating the so-called factor-by-curve interaction. A local scoring algorithm based on local linear kernel smoothers was used to estimate the model. Two different types of bootstrap-based procedures are proposed for testing interaction terms, namely, the likelihood ratio test, and a procedure based on an estimate of the interaction terms. Given the high computational cost involved, binning techniques were used to speed up computation in the estimation and testing processes. A simulation study was conducted to assess the validity of these bootstrap-based tests. This methodology was applied to studying prefrontal cortex neural activity associated with decision-making in monkeys. The proposed statistical procedure proved very useful in revealing the neural activity correlates of decision-making strategies adopted by monkeys in accordance with different behavioural tasks.

Action Potentials↗