Time-Frequency Analysis of Heart Rate Variability for Neonatal Seizure Detection
- PDF / 1,010,641 Bytes
- 10 Pages / 600.03 x 792 pts Page_size
- 105 Downloads / 158 Views
Research Article Time-Frequency Analysis of Heart Rate Variability for Neonatal Seizure Detection M. B. Malarvili,1 Mostefa Mesbah,1 and Boualem Boashash1, 2 1 Perinatal
Research Centre, School of Medicine, University of Queensland, Herston, QLD 4029, Australia Processing Research Center, Department of Electrical and Computer Engineering, College of Engineering, University of Sharjah, P.O. Box 27272, Sharjah, United Arab Emirates
2 Signal
Received 1 May 2006; Revised 29 January 2007; Accepted 2 February 2007 Recommended by Pablo Laguna Lasaosa There are a number of automatic techniques available for detecting epileptic seizures using solely electroencephalogram (EEG), which has been the primary diagnosis tool in newborns. The electrocardiogram (ECG) has been much neglected in automatic seizure detection. Changes in heart rate and ECG rhythm were previously linked to seizure in case of adult humans and animals. However, little is known about heart rate variability (HRV) changes in human neonate during seizure. In this paper, we assess the suitability of HRV as a tool for seizure detection in newborns. The features of HRV in the low-frequency band (LF: 0.03–0.07 Hz), mid-frequency band (MF: 0.07–0.15 Hz), and high-frequency band (HF: 0.15–0.6 Hz) have been obtained by means of the timefrequency distribution (TFD). Results of ongoing time-frequency (TF) research are presented. Based on our preliminary results, the first conditional moment of HRV which is the mean/central frequency in the LF band and the variance in the HF band can be used as a good feature to discriminate the newborn seizure from the nonseizure. Copyright © 2007 M. B. Malarvili et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
1.
INTRODUCTION
Neonatal epileptic seizures are major indicators of a number of central nervous system (CNS) disorders. A careful assessment of seizures is needed at the early stage to prevent further damages to the brain [1]. Growing attention is focused on the development of computerized methods to automatically detect newborn seizure based on the EEG. There are a number of techniques available for detecting neonatal EEG seizures in the time [2], frequency [3], and time-frequency [4] domains. However, neonatal seizure recognition remains a very challenging task and lacks a reliable detection scheme for clinical use [5]. There is a new tendency towards using information from different physiological signals such as ECG, respiration, and blood pressure to detect seizure [6–9]. This extra information is expected to enhance the performance and robustness of the seizure detectors. This is in line with our longterm goal of using information from different physiological signals such as EEG, ECG, blood pressure, respiration, and oxygen saturation to robustly detect seizures in newborns. Continuous monitoring of the newborn ECG and heart rate have been successful
Data Loading...
