TY - GEN
T1 - Detection of neonatal seizure using multiple filters
AU - Khlif, M. S.
AU - Mesbah, M.
AU - Boashashl, B.
AU - Colditz, P.
PY - 2010
Y1 - 2010
N2 - It is often impossible to accurately differentiate between seizure and non-seizure related activities in irifants based on clinical manifestations alone. The electroencephalogram (EEG) is therefore the best tool available for the recognition, management, and prognosis of neonatal seizures. The EEG signal is known to change structural characteristics between seizure and non-seizure states. In this work, matching pursuit (MP) decomposition, based on a coherent time-frequency (TF) dictionary, has provided us with a measure for quantifying changes in the structure of the neonatal EEG signal as it alternates between the various states. The quantification of state changes served as the basis for detecting seizures in 35 newborn patients. For each record, a patient-dependent threshold that marks the transition to seizure state is established. The use of multiple filters reduced the amount of artifacts and enhanced the detector performance. Overall, 93.4% detection accuracy and 0.26 false alarms per hour were achieved.
AB - It is often impossible to accurately differentiate between seizure and non-seizure related activities in irifants based on clinical manifestations alone. The electroencephalogram (EEG) is therefore the best tool available for the recognition, management, and prognosis of neonatal seizures. The EEG signal is known to change structural characteristics between seizure and non-seizure states. In this work, matching pursuit (MP) decomposition, based on a coherent time-frequency (TF) dictionary, has provided us with a measure for quantifying changes in the structure of the neonatal EEG signal as it alternates between the various states. The quantification of state changes served as the basis for detecting seizures in 35 newborn patients. For each record, a patient-dependent threshold that marks the transition to seizure state is established. The use of multiple filters reduced the amount of artifacts and enhanced the detector performance. Overall, 93.4% detection accuracy and 0.26 false alarms per hour were achieved.
KW - EEG
KW - Matching pursuit
KW - Newborn
KW - Seizure
KW - Time-frequency
UR - http://www.scopus.com/inward/record.url?scp=78650272910&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=78650272910&partnerID=8YFLogxK
U2 - 10.1109/ISSPA.2010.5605469
DO - 10.1109/ISSPA.2010.5605469
M3 - Conference contribution
AN - SCOPUS:78650272910
SN - 9781424471676
T3 - 10th International Conference on Information Sciences, Signal Processing and their Applications, ISSPA 2010
SP - 284
EP - 287
BT - 10th International Conference on Information Sciences, Signal Processing and their Applications, ISSPA 2010
T2 - 10th International Conference on Information Sciences, Signal Processing and their Applications, ISSPA 2010
Y2 - 10 May 2010 through 13 May 2010
ER -