From EHG signals to graphs: A new method for predicting premature birth.
Résumé
The objective of this paper is to present the framework of an advanced approach aiming at characterizing the electrohysterographic (EHG) signals recorded during pregnancy and labor. The approach is based on the analysis of the propagation of the uterine electrical activity. The processing include i) the estimation of the statistical independences between the recorded EHG signals, ii) the characterization of the obtained connectivity matrices using network measures (graph-theory based analysis) and iii) the use of these measures in clinical application: the classification of signals recorded during pregnancy and labor. However, a number of methodological questions are still open regarding the optimal way to process the data in order to achieve the clinical application. In this abstract we tackle one of these issues related to the connectivity methods to be used in order to produce the connectivity matrices. We evaluate more than one method using a physiological uterine EMG model developed recently in our team.
Origine | Fichiers produits par l'(les) auteur(s) |
---|