Comparison of Three Methods for Classifying Burst and Suppression in the EEG of Post Asphyctic Newborns
Paper in proceeding, 2007
Fisher's linear discriminant, a feed-forward neural network (NN) and a support vector machine (SVM) are compared with respect to their ability to distinguish bursts from suppression in burst-suppression electroencephalogram (EEG) signals using five features inherent in the EEG as input. The study is based on EEG signals from six full term infants who have suffered from perinatal asphyxia, and the methods have been trained with reference data classified by an experienced electroencephalographer. The results are summarized as area under the curve (AUC) values derived from receiver operating characteristic (ROC) curves for the three methods, and show that the SVM is slightly better than the others, at the cost of a higher computational complexity.
Male
Artificial Intelligence
Sensitivity and Specificity
Asphyxia Neonatorum
methods
Chronic
Reproducibility of Results
etiology
Newborn
methods
diagnosis
methods
complications
Algorithms
Classification
Pattern Recognition
Diagnosis
Humans
Brain Damage
Computer-Assisted
Automated
Electroencephalography
Infant
Biomedical Signal Processing
diagnosis
Author
Johan Löfhede
Chalmers, Signals and Systems, Signal Processing and Biomedical Engineering
Nils Löfgren
Magnus Thordstein
University of Gothenburg
Anders Flisberg
University of Gothenburg
Ingemar Kjellmer
University of Gothenburg
Kaj Lindecrantz
Chalmers, Signals and Systems, Signal Processing and Biomedical Engineering
Engineering in Medicine and Biology Society, 2007. EMBS 2007. 29th Annual International Conference of the IEEE
1557-170X (ISSN)
5136 - 5139978-1-4244-0788-0 (ISBN)
Subject Categories
Medical Laboratory and Measurements Technologies
Physiology
ISBN
978-1-4244-0788-0