Detecting Labor using Graph Theory on Connectivity Matrices of Uterine EMG - Université de Rennes Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

Detecting Labor using Graph Theory on Connectivity Matrices of Uterine EMG

Résumé

Premature labor is one of the most serious health problems in the developed world. One of the main reasons for this is that no good way exists to distinguish true labor from normal pregnancy contractions. The aim of this paper is to investigate if the application of graph theory techniques to multi-electrode uterine EMG signals can improve the discrimination between pregnancy contractions and labor. To test our methods we first applied them to synthetic graphs where we detected some differences in the parameters results and changes in the graph model from pregnancy-like graphs to labor-like graphs. Then, we applied the same methods to real signals. We obtained the best differentiation between pregnancy and labor through the same parameters. Major improvements in differentiating between pregnancy and labor were obtained using a low pass windowing preprocessing step. Results show that real graphs generally became more organized when moving from pregnancy, where the graph showed random characteristics, to labor where the graph became a more small-world like graph
Fichier non déposé

Dates et versions

hal-01304748 , version 1 (20-04-2016)

Identifiants

  • HAL Id : hal-01304748 , version 1

Citer

S. Al-Omar, A. Diab, N. Nader, M. Khalil, B. Karlsson, et al.. Detecting Labor using Graph Theory on Connectivity Matrices of Uterine EMG. 2015 37th annual international conference of the IEEE Engineering in Medicine and Biology Society, 2015, Milan, Italy. pp.2195--2198. ⟨hal-01304748⟩
44 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More