DocumentCode :
2925982
Title :
Improving the classification rate of labor vs. normal pregnancy contractions by using EHG multichannel recordings
Author :
Hassan, M. ; Terrien, J. ; Alexandersson, Asgeir ; Marque, C. ; Karlsson, B.
fYear :
2010
fDate :
Aug. 31 2010-Sept. 4 2010
Firstpage :
4642
Lastpage :
4645
Abstract :
Most of the studies on the synchronization between EHG signals, recorded during the same contractions at different locations, are limited to the use of only two channels. Multichannel techniques have however been widely applied to EEG signals but rarely to EHG. In this paper, we investigate the use of multichannel uterine EMG signals for classifying contractions. We compare the performance of phase synchronization in distinguishing between labor and normal pregnancy contractions by using either only two channels or a 4×4 matrix positioned on the woman´s abdomen. We used two indexes to measure the phase synchronization: mean phase coherence and phase entropy. ROC curves indicate that the use of multichannel signals can significantly improve the classification rate of pregnancy and labor contractions.
Keywords :
biomechanics; electromyography; entropy; medical signal processing; obstetrics; sensitivity analysis; signal classification; synchronisation; EHG multichannel recordings; ROC curves; abdomen; classification rate; labor contractions; mean phase coherence; multichannel uterine EMG signals; normal pregnancy contractions; phase entropy; phase synchronization; signal classification; Coherence; Correlation; Electromyography; Entropy; Pregnancy; Sensitivity; Synchronization; Algorithms; Diagnosis, Computer-Assisted; Electromyography; Female; Humans; Labor Onset; Myometrium; Pattern Recognition, Automated; Pregnancy; Uterine Contraction;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Engineering in Medicine and Biology Society (EMBC), 2010 Annual International Conference of the IEEE
Conference_Location :
Buenos Aires
ISSN :
1557-170X
Print_ISBN :
978-1-4244-4123-5
Type :
conf
DOI :
10.1109/IEMBS.2010.5626486
Filename :
5626486
Link To Document :
بازگشت