Please use this identifier to cite or link to this item:
Title: Detecting hypermotor seizures using extreme value statistics
Authors: LUCA, Stijn 
Karsmakers, Peter
Cuppens, Kris
Croonenborghs, Tom
Van de Vel, Anouk
Ceulemans, Berten
Lagae, Lieven
Van Huffel, Sabine
Vanrumste, Bart
Issue Date: 2012
Source: Leuven Statistical Days: Mixed models and modern multivariate methods in linguistics., Leuven, Belgium, 7-8 June 2012
Abstract: Nocturnal home monitoring of epileptic children is often not feasible due to the cumbersome manner of seizure detection with the standard method of video/EEG-monitoring. We propose a method for hypermotor seizure detection based on accelerators attached to the extremities. Hypermotor seizures often involve violent movements with the arms or legs, which increases the need for an alarm system as the patient can injure himself during the seizure. In the literature, classification models are commonly estimated in a supervised manner. Such models are estimated using annotated examples. This annotation of data requires expert (human) interaction and results therefore in a substantial cost in the estimation process of the seizure detection model. In this work we propose the use of an unsupervised approach for estimating seizure detection models. Our method does not require any annotation of data while obtaining state-of-the-art classification scores that are comparable to those of a model estimated in a supervised manner. The proposed methodology is based on extreme value statistics. Since epileptic seizures are rare compared to normal movements, all recorded data can be used to estimate a model of normality. The very few abnormal events have a negligible effect. As a consequence, a person-dependent epileptic seizure detector can be estimated with little human interaction. After segmenting the acquired acceleration signals in movement events, features are extracted for further processing. On the basis of the preprocessed data a classification model for discriminating epileptic and non-epileptic movement events is estimated. Using this approach we were able to detect hypermotor seizures in two patients with a sensitivity of 100.00% and a PPV of 85.4% for one patient, and 98.8% and 79.1% for the sensitivity and PPV respectively for the other patient. We also found that an increase of the number of features did not increase the performance substantially.
Document URI:
Link to publication:
Category: C2
Type: Conference Material
Appears in Collections:Research publications

Show full item record

Page view(s)

checked on May 22, 2022

Google ScholarTM


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.