Classification of uterine EMG signals using supervised classification method

Mohamad O. Diab, Amira El-Merhie, Nour El-Halabi, Layal Khoder

.

DOI: 10.4236/jbise.2010.39113                

Abstract

Aim: The main purpose of this article is to detect any risk of preterm deliveries at an early gestation period using uterine electromyography signals. Detecting such uterine signals can yield a promising approach to determine and take actions to prevent this potential risk. Methods: The best position for the detection of different uterine signals is the median vertical axis of the abdomen. These signals differ from each other by their frequency content. Initially, simulation is done for the real detected EMG signals: preterm deliveries (PD) EMGs and deliveries at term (DT) EMGs. This is performed by applying autoregressive model (AR) of specific order to estimate AR coefficients of these real EMG signals. Finally, after calculation of the AR parameters of the two types of deliveries, we generate two types of simulated uterine contractions by using White Gaussian Noise (WGN). Frequency parameter extraction and classification are first applied on simulated signals to test the limits and performance of the used methods. The last remaining step is the classification of the contractions using supervised classification method. Results: Results show that uterine contractions may be classified using the Artificial Neural Networks (ANNs). The Simple Perceptron ANN is applied on the signals for their supervised classification into independent groups: preterm deliveries (PD) and deliveries at term (TD) according to their frequency content.

Keywords

Uterine EMG Signals; AR Model; PSD; ANN

Conflicts of Interest

The authors declare no conflicts of interest.

References

[1]	Mckean, M., Walters, A.W.W. and Smith, R. (1993) Prediction and early diagnosis of preterm labor: A critical review. Obstetrical & Gynecological Survey, 48(4), 209-225.
[2]	Senat, M.V., Tsatsaris, V., Ville, Y. And Fernandez, H. (1999) Menaced’accouchement prématuré. Encycl Méd Chir (Elsevier, Paris), Urgences, 17.
[3]	Marque, C.K., Terrien, J., Rihana, S. and Germai, G. (2007) Preterm labour detection by use of a biophysical marker: The uterine electrical activity. BMC Pregnancy and Childbirth.
[4]	Newman, R.B., Gill, P.J., Campion, S. and Katz, M. (1987) Antepartum ambulatory tocodynamometry: The significance of low-amplitude, high-frequency contractions. Obstetrics & Gynecology, 70(5), 701-750.
[5]	Marque, C., Duchêne, J., Leclercq, S., et al. (1986) Uterine EHG processing for obstetrical monitoring. IEEE Transactions on Biomedical Engineering, 33(12), 1182- 1187.
[6]	Diab, M.O., Marque, C. and Khalil, M.A. (2007) Classification for uterine EMG signals: Comparison between AR model and statistical classification method. International Journal of computational cognition, 5(1), 8-14.
[7]	Khalil, M. and Duchene, J. (1999) Detection and classification of multiple events in piecewise stationary signals: Comparison between autoregressive and multiscale approaches. Signals processing, 75(3), 239-251.
[8]	Hayes, M. (1996) Statistical digital signal processing and modelling. John Wiley & Sons, Georgia Institute of Technology.
[9]	Kay, S. (1988) Modern spectral estimation theory and application. Englewood Cliffs, Prentice-Hall, New Jersey.
[10]	Gurney, K. (1997) An introduction to neural networks, University College London Press.
[11]	Lockwood, C.J. and Kuczynski, E. (2001) Risk stratification and pathological mechanisms in preterm delivery. Paediatric and Perinatal Epidemiology, 15(Suppl 2), 78-89.
[12]	Iams, J.D. (2003) Prediction and early detection of preterm labor. American Journal of Obstetrics & Gynecology, 101(2), 402-412.
[13]	Linhart, J., Olson, G., Goodrum, L., Rowe, T., Saade, G. and Hankins, G. (1990) Preterm labor at 32 to 34 weeks gestation: Effect of a policy of expectant management on length of gestation. American Journal of Obstetrics & Gynecology, 178-179.