TY - JOUR
T1 - Newborn seizure detection based on heart rate variability
AU - Malarvili, M. B.
AU - Mesbah, Mostefa
N1 - Funding Information:
Manuscript received November 24, 2008; revised March 17, 2009 and April 27, 2009. First published July 21, 2009; current version published October 16, 2009. This work was supported in part by the Australian Research Council’s Discovery and Linkage Funding Schemes (DP0665697 and LP0562317). Asterisk indicates corresponding author.
PY - 2009/11
Y1 - 2009/11
N2 - In this paper, we investigate the use of heart rate variability (HRV) for automatic newborn seizure detection. The proposed method consists of a sequence of processing steps, namely, obtaining HRV from the ECG, extracting a discriminating HRV feature set, selecting an optimal subset from the full feature set, and, finally, classifying the HRV into seizure/nonseizure using a supervised statistical classifier. Due to the fact that HRV signals are nonstationary, a set of timefrequency features from the newborn HRV is proposed and extracted. In order to achieve efficient HRV-based automatic newborn seizure detection, a two-phase wrapper-based feature selection technique is used to select the feature subset with minimum redundancy and maximum class discriminability. Tested on ECG recordings obtained from eight newborns with identified EEG seizure, the proposed HRV-based neonatal seizure detection algorithm achieved 85.7 sensitivity and 84.6 specificity. These results suggest that the HRV is sensitive to changes in the cardioregulatory system induced by the seizure, and therefore, can be used as a basis for an automatic seizure detection.
AB - In this paper, we investigate the use of heart rate variability (HRV) for automatic newborn seizure detection. The proposed method consists of a sequence of processing steps, namely, obtaining HRV from the ECG, extracting a discriminating HRV feature set, selecting an optimal subset from the full feature set, and, finally, classifying the HRV into seizure/nonseizure using a supervised statistical classifier. Due to the fact that HRV signals are nonstationary, a set of timefrequency features from the newborn HRV is proposed and extracted. In order to achieve efficient HRV-based automatic newborn seizure detection, a two-phase wrapper-based feature selection technique is used to select the feature subset with minimum redundancy and maximum class discriminability. Tested on ECG recordings obtained from eight newborns with identified EEG seizure, the proposed HRV-based neonatal seizure detection algorithm achieved 85.7 sensitivity and 84.6 specificity. These results suggest that the HRV is sensitive to changes in the cardioregulatory system induced by the seizure, and therefore, can be used as a basis for an automatic seizure detection.
KW - EEG
KW - Heart rate variability (HRV)
KW - Newborn seizure
KW - Pattern recognition
UR - http://www.scopus.com/inward/record.url?scp=70449378583&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=70449378583&partnerID=8YFLogxK
U2 - 10.1109/TBME.2009.2026908
DO - 10.1109/TBME.2009.2026908
M3 - Article
C2 - 19628449
AN - SCOPUS:70449378583
SN - 0018-9294
VL - 56
SP - 2594
EP - 2603
JO - IEEE Transactions on Biomedical Engineering
JF - IEEE Transactions on Biomedical Engineering
IS - 11
M1 - 5170066
ER -