- Personalizing Heart Rate-Based Seizure Detection Using Supervised SVM Transfer Learning
De Cooman, Thomas; Vandecasteele, Kaat; Varon, Carolina; Hunyadi, Borbala; Cleeren, Evy; Van Paesschen, Wim; Van Huffel, Sabine;
Frontiers in Neurology,
Volume 11, pp. 145, 2020. DOI: 10.3389/fneur.2020.00145
- Development of temporal lobe epilepsy during maintenance electroconvulsive therapy: A case of human kindling?
C. Schotte; E. Cleeren; K. Goffin; B. Hunyadi; S. Buggenhout; K. Van Laere; W. Van Paesschen;
Volume 4, Issue 1, pp. 200-205, 2019. DOI: 10.1002/epi4.12294
- Semi-automated EEG enhancement improves localization of ictal onset zone with EEG-correlated fMRI
S. Van Eyndhoven; B. Hunyadi; P. Dupont; W. Van Paesschen; S. Van Huffel;
Frontiers in Neurology,
Volume 10, 2019. DOI: 10.3389/fneur.2019.00805
- Nonconvulsive epileptic seizure monitoring with incremental learning
Y.R. Rodriguez Aldana; E.J. Maranon Reyes; F. Sanabria Macias; V. Rodriguez Rodriguez; L. Morales Chacon; S. Van Huffel; B. Hunyadi;
Computers in Biology and Medicine,
Volume 114, pp. 103434, 2019. ISSN 0010-4825. DOI: 10.1016/j.compbiomed.2019.103434
Keywords: ...Nonconvulsive epileptic seizures, Hilbert huang transform, Multiway data analysis, Incremental learning.
Abstract: ...Nonconvulsive epileptic seizures (NCSz) and nonconvulsive status epilepticus (NCSE) are two neurological entities associated with increment in morbidity and mortality in critically ill patients. In a previous work, we introduced a method which accurately detected NCSz in EEG data (referred here as ‘Batch method’). However, this approach was less effective when the EEG features identified at the beginning of the recording changed over time. Such pattern drift is an issue that causes failures of automated seizure detection methods. This paper presents a support vector machine (SVM)-based incremental learning method for NCSz detection that for the first time addresses the seizure evolution in EEG records from patients with epileptic disorders and from ICU having NCSz. To implement the incremental learning SVM, three methodologies are tested. These approaches differ in the way they reduce the set of potentially available support vectors that are used to build the decision function of the classifier. To evaluate the suitability of the three incremental learning approaches proposed here for NCSz detection, first, a comparative study between the three methods is performed. Secondly, the incremental learning approach with the best performance is compared with the Batch method and three other batch methods from the literature. From this comparison, the incremental learning method based on maximum relevance minimum redundancy (MRMR_IL) obtained the best results. MRMR_IL method proved to be an effective tool for NCSz detection in a real-time setting, achieving sensitivity and accuracy values above 99%.