Download PDF

CinC 2015, Date: 2015/09/01 - 2015/09/01, Location: Nice, France

Publication date: 2015-09-01
Volume: 42 Pages: 977 - 980
ISSN: 9781509006854
Publisher: IEEE

Proc. of the 42nd Annual Computing in Cardiology

Author:

De Cooman, Thomas
Van de Vel, A ; Ceulemans, B ; Lagae, Lieven ; Van Paesschen, Wim ; Vanrumste, Bart ; Van Huffel, Sabine

Keywords:

SISTA, Science & Technology, Technology, Computer Science, Interdisciplinary Applications, Engineering, Multidisciplinary, Engineering, Biomedical, Computer Science, Engineering

Abstract:

© 2015 CCAL. Previous studies have shown that during several types of seizures, the heart rate increases strongly towards a maximal patient-specific epileptic heart rate HRep. This ictal peak heart rate is one of the most important features for classifying epileptic heart rate increases. We therefore try to estimate HRep, which is done by using least squares support vector machines. The found estimation had a mean square error of 18bpm, which is an improvement compared to age-based estimators. Adding this information to an online seizure detector led to an increased performance (F1-score: 14.65% to 18.72%) with a decreased detection delay (23.8s to 11.9s).