Prediction of Term Labor Using Wavelet Analysis of Uterine Magnetomyography Signals

  • T. Ananda BabuEmail author
  • P. Rajesh Kumar
Conference paper
Part of the Lecture Notes on Data Engineering and Communications Technologies book series (LNDECT, volume 28)


The objective of the research is to predict the term labor by analyzing the uterine magnetomyography signals of term labor. Previous work limited to the detection of uterine contractions by extracting the features. To date, the existing research for labor prediction did not achieve high discrimination accuracy that a clinical application requires. Discrete wavelet transform is used in the research to decompose the signals. Variance, standard deviation, waveform length, energy, and entropy of wavelet coefficients are extracted from the signals of the Physionet mmgdb database. The features were divided into labor and antepartum groups. Five different classifiers were implemented to discern the two groups. Wavelet coefficient features combined with the random subspace ensemble classifier produced a powerful tool for labor assessment.


Labor prediction Magnetomyography (MMG) Physionet mmgdb database Discrete wavelet transform (DWT) Random subspace ensemble classifier 


  1. 1.
    Gondry J, Duchene J, Marque C (1992) First results on uterine EMG monitoring during pregnancy. Proc Ann Int Conf IEEE EMBS 6:2609–2610Google Scholar
  2. 2.
    Eswaran H, Preissl H, Wilson JD, Murphy P, Lowery CL (2004) Prediction of labor in term and preterm pregnancies using non-invasive magnetomyographic recordings of uterine contractions. Am J of Obstet Gynecol 190(6):1598–1603CrossRefGoogle Scholar
  3. 3.
    Eswaran H, Preissl H, Wilson JD, Murphy P, Robinson SE, Lowery CL (2002) First magnetomyographic recordings of uterine activity with spatial temporal information with a 151-channel sensor array. Am J Obstet Gynecol 187:145–151CrossRefGoogle Scholar
  4. 4.
    Horoba K, Jezewski J, Wrobel J Graczyk S (2001) Algorithm for detection of uterine contractions from electrohysterogram. In: Proceedings. 23rd international conference IEEE EMBS, pp 461–464Google Scholar
  5. 5.
    Lucovnik M, Kuon RJ, Garfield RE (2011) Use of uterine electromyography to diagnose term and preterm labor. Acta Obstet Gynecol Scand 90(2):150–157CrossRefGoogle Scholar
  6. 6.
    Lucovnik M, Maner WM, Chambliss LR, Blumrick R, Balducci J, Novak-Antolic Z et al (2011) Noninvasive uterine electromyography for prediction of preterm delivery. Am J of Obstet Gynecol. 204(3):228CrossRefGoogle Scholar
  7. 7.
    Rabotti C, Mischi M, Oei SG, Bergmans JWM (2010) Noninvasive estimation of the electro hysterographic action-potential conduction velocity. IEEE Trans Biomed Eng 57(9):2178–2187CrossRefGoogle Scholar
  8. 8.
    Ramon C, Preissl H, Murphy P, Wilson JD, Lowery CL, Eswaran H (2005) Synchronization analysis of the uterine magnetic activity during contractions. Biomed Eng Online 4:55CrossRefGoogle Scholar
  9. 9.
    La Rosa PS, Nehorai A, Eswaran H, Lowery CL, Preissl H (2008) Detection of uterine MMG contractions using a multiple change point estimator and the k-means cluster algorithm. IEEE Trans Biomed Eng 55:453–467CrossRefGoogle Scholar
  10. 10.
    Garfield RE, Maner WL, MacKay LB, Schlembach D, Saade GR (2005) Comparing uterine electromyography activity of antepartum patients versus term labor patients. Am J Obstet Gyn 193:23–29CrossRefGoogle Scholar
  11. 11.
    Furdea A, Eswaran H, Wilson JD, Preissl H, Lowery CL, Govindan RB (2009) Magnetomyographic recording and identification of uterine contractions using Hilbert-wavelet transforms. Physiol Meas 30(10):1051–1060CrossRefGoogle Scholar
  12. 12.
    Furdea A, Preissl H, Lowery CL, Eswaran H, Govindan RB (2011) Conduction velocity of the uterine contraction in serial magnetomyogram (MMG) data: event based simulation and validation. In: 2011 conference proceedings IEEE EMBS, pp 6025–6028Google Scholar
  13. 13.
    Escalona-Vargas D, Govindan RB, Furdea A, Murphy P, Lowery CL, Eswaran H (2015) Characterizing the propagation of uterine electrophysiological signals recorded with a multi sensor abdominal array in term pregnancies. PLoS ONE 10(10):e0140894. Scholar
  14. 14.
    Govindan RB, Siegel E, Mckelvey S, Murphy P, Lowery CL, Eswaran H (2015) Tracking the changes in synchrony of the electrophysiological activity as the uterus approaches labor using magnetomyographic technique. Reprod Sci 22(5):595–601CrossRefGoogle Scholar
  15. 15.
    Govindan RB, Vairavan S, Furdea A, Murphy P, Preissl H (2010) Decrement of uterine myometrial burst duration as a correlate to active labor: a Hilbert phase approach. In: 32nd Annual international conference of the IEEE EMBSGoogle Scholar
  16. 16.
    Maner WL, Garfield RE (2007) Identification of human term and preterm labor using artificial neural networks on uterine electromyography data. Ann Biomed Eng 35(3):465–473CrossRefGoogle Scholar
  17. 17.
    Ren P, Yao S, Li J, Valdes-Sosa PA, Kendrick KM (2015) Improved prediction of preterm delivery using empirical mode decomposition analysis of uterine electromyography signals. PLoS ONE 10(7):e0132116. Scholar
  18. 18.
    Goldberger AL, Amaral LA, Glass L, Hausdorff JM, Ivanov PC, Mark RG, Mietus JE, Moody GB, Peng C-K, Stanley HE (2000) PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation 101(23), e215–e220[circulation electronic pages;

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.Department of ECE, AUCE (A)Andhra UniversityVisakhapatnamIndia

Personalised recommendations