TY - JOUR
T1 - Automatic seizure detection based on the combination of newborn multi-channel EEG and HRV information Advances in Nonstationary Electrophysiological Signal Analysis and Processing
AU - Mesbah, Mostefa
AU - Balakrishnan, Malarvili
AU - Colditz, Paul B.
AU - Boashash, Boualem
N1 - Funding Information:
The authors would like to acknowledge Dr. Chris Burke and Ms. Jane Richmond from the Royal Children’s Hospital, Brisbane, Australia, for their assistance in recording, labeling, and interpreting the data used in this study. This study was partly funded by an Australian Research Council Discovery grant (DP0665697) until 2009, and after that by QNRF under NPRP-09-465-2-174.
PY - 2012
Y1 - 2012
N2 - This article proposes a new method for newborn seizure detection that uses information extracted from both multi-channel electroencephalogram (EEG) and a single channel electrocardiogram (ECG). The aim of the study is to assess whether additional information extracted from ECG can improve the performance of seizure detectors based solely on EEG. Two different approaches were used to combine this extracted information. The first approach, known as feature fusion, involves combining features extracted from EEG and heart rate variability (HRV) into a single feature vector prior to feeding it to a classifier. The second approach, called classifier or decision fusion, is achieved by combining the independent decisions of the EEG and the HRV-based classifiers. Tested on recordings obtained from eight newborns with identified EEG seizures, the proposed neonatal seizure detection algorithms achieved 95.20% sensitivity and 88.60% specificity for the feature fusion case and 95.20% sensitivity and 94.30% specificity for the classifier fusion case. These results are considerably better than those involving classifiers using EEG only (80.90%, 86.50%) or HRV only (85.70%, 84.60%).
AB - This article proposes a new method for newborn seizure detection that uses information extracted from both multi-channel electroencephalogram (EEG) and a single channel electrocardiogram (ECG). The aim of the study is to assess whether additional information extracted from ECG can improve the performance of seizure detectors based solely on EEG. Two different approaches were used to combine this extracted information. The first approach, known as feature fusion, involves combining features extracted from EEG and heart rate variability (HRV) into a single feature vector prior to feeding it to a classifier. The second approach, called classifier or decision fusion, is achieved by combining the independent decisions of the EEG and the HRV-based classifiers. Tested on recordings obtained from eight newborns with identified EEG seizures, the proposed neonatal seizure detection algorithms achieved 95.20% sensitivity and 88.60% specificity for the feature fusion case and 95.20% sensitivity and 94.30% specificity for the classifier fusion case. These results are considerably better than those involving classifiers using EEG only (80.90%, 86.50%) or HRV only (85.70%, 84.60%).
KW - Classifier combination
KW - EEG
KW - Features fusion
KW - Heart rate variability
KW - IF
KW - MBD
KW - Newborn seizure
KW - Seizure detection
KW - TFD
KW - Time-frequency representation
UR - http://www.scopus.com/inward/record.url?scp=84887074890&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84887074890&partnerID=8YFLogxK
U2 - 10.1186/1687-6180-2012-215
DO - 10.1186/1687-6180-2012-215
M3 - Article
AN - SCOPUS:84887074890
SN - 1687-6172
VL - 2012
JO - Eurasip Journal on Advances in Signal Processing
JF - Eurasip Journal on Advances in Signal Processing
IS - 1
M1 - 215
ER -