Multivariate Time–Frequency Analysis of Electrohysterogram for Classification of Term and Preterm Labor

  • Jiwoo You
  • Youngjoo Kim
  • Woojoon Seok
  • Seungmin Lee
  • Donggyu Sim
  • Kwang Suk Park
  • Cheolsoo ParkEmail author
Original Article


Non-invasive electrohysterogram (EHG) could be a promising technique for the preterm birth prediction, which could enable us to diagnose the preterm birth before the labor and reduces the infant mortality and morbidity. Previous studies on the preterm birth prediction with EHG have conducted comprehensive researches on various signal features and classification algorithms, but most of them adopted prefilters based on the linear transforms using fixed basis function, although they are suboptimal for the nonlinearity and nonstationarity of the EHG signal. In this paper, multivariate empirical mode decomposition (MEMD) is applied to decompose the electrical activity signal measured on the uterus. After the decomposition, features are calculated for the corresponding oscillations to the uterine contraction. To investigate the performance of the features, three-channel EHG signals of 254 patients (224 term, 30 preterm) are chosen among 300 patients from Physionet term-preterm electrohysterogram (TPEHG) database to extract features from the EHG signals and classify the features using machine learning algorithms. Classification results shows that the proposed method with MEMD achieved 94.66% correctly classified rate (CCR) and 0.987 area under the curve (AUC), which outperformed those with IIR filter implying MEMD provides a new prospect to improve the current preterm birth prediction approach.


Preterm birth detection EHG Uterine EMG Machine learning classification NA-MEMD 



This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science and ICT (NRF-2017R1A5A1015596), the Ministry of Education (NRF-2017R1D1A1B03031485) and the Research Grant of Kwangwoon University in 2019.


  1. 1.
    World Health Organization (2012) Born too soon: the global action report on preterm birth, pp 1–111Google Scholar
  2. 2.
    Guyer B, MacDorman MF, Martin Kimberley JA, Peters D, Strobino DM (1998) Annual summary of vital statistics-1997, pp 1333–1349Google Scholar
  3. 3.
    Garfield RE, Lucovnik M, Kuon RJ (2014) Diagnosis and effective management of preterm labor. MGM J Med Sci 1:22–37Google Scholar
  4. 4.
    Lucovnik M, Chambliss LR, Garfield RE (2013) Costs of unnecessary admissions and treatments for threatened preterm labor. Am J Obstetr 209(3):217.e1–217.e3Google Scholar
  5. 5.
    Lucovnik M, Chambliss LR, Garfield RE (2014) The sky high costs of air ambulance transport of patients in suspected preterm labor reproductive science. 21(3):2455Google Scholar
  6. 6.
    Devedeux D, Marque C, Mansour S, Germain G, Duchene J (1993) Uterine electromyography: a critical review. Am J Obstet Gynecol 169(6):1636–1653Google Scholar
  7. 7.
    Planes JG, Morucci JP, Grandjean H, Favretto R (1984) External recording and processing of fast electrical activity of the uterus in human parturition. Med Biol Eng Comput 22(6):585–591Google Scholar
  8. 8.
    Rabotti C, Mischi M, Beulen L, Oei G, Bergmans JWM (2010) Modeling and identification of the electrohysterographic volume conductor by high-density electrodes. IEEE Trans Biomed Eng 57(3):519–527Google Scholar
  9. 9.
    Rooijakkers MJ, Rabotti C, Oei G, Aarts RM, Mischi M (2014) Low-complexity intrauterine pressure estimation using the Teager energy operator on electrohysterographic recordings. Physiol Meas 35(7):1215Google Scholar
  10. 10.
    Shi SQ, Maner WL, Mackay LB, Garfield RE (2008) Identification of term and pre-term labor in rats using artificial neural networks on uterine EMG signals. Am J Obstet Gynecol 198(2):235.e1-234.e4Google Scholar
  11. 11.
    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 Gynecol 193(1):23–29Google Scholar
  12. 12.
    Diab MO, Marque C, Khalil MA (2007) Classification of uterine EMG signals: comparison between AR model and statistical classification method. Int J Comput Cognit 5(1):8–14Google Scholar
  13. 13.
    Moslem B, Diab M, Khalil M, Marque C (2012) Combining data fusion with multiresolution analysis for improving the classification accuracy of uterine EMG signals. EURASIP J Adv Signal Process 2012(1):167Google Scholar
  14. 14.
    Baghamoradi SMS, Naji M, Aryadoost H (2011) Evaluation of cepstral analysis of EHG signals to prediction of preterm labor. 18th Iranian Conference on Biomedical Engineering, pp 81–83Google Scholar
  15. 15.
    Sim S, Ryu H, Kim H, Han J, Park K (2013) Evaluation of electrohysterogram feature extraction to classify the preterm and term delivery groups. The 15th International Conference on Biomedical Engineering, pp 675–678Google Scholar
  16. 16.
    Fergus P, Cheung P, Hussain A, Al-Jumeily D, Dobbins C, Iram S (2013) Prediction of preterm deliveries form EHG signals using machine learning. PLoS One 8(10):e77154Google Scholar
  17. 17.
    Naeem SM, Seddik AF, Eldosoky MA (2014) New technique based on uterine electromyography nonlinearity for preterm delivery detection. J Eng Technol Res 6(7):107–114Google Scholar
  18. 18.
    Fele-Zorz G, Kavsek G, Novak-Antolic Z, Jager F (2008) A comparison of various linear and non-linear signal processing techniques to separate uterine EMG records of term and pre-term delivery groups. Med Biol Eng Comput 46(9):911–922Google Scholar
  19. 19.
    Verdenik I, Pajntar M, Leskosek B (2001) Uterine electrical activity as predictor of preterm birth in women with preterm contractions. Eur J Obstetr Gynecol Reprod Biol 95(2):149–153Google Scholar
  20. 20.
    Buhimschi C, Boyle MB, Garfield RE (1997) Electrical activity of the human uterus during pregnancy as recorded from the abdominal surface. Obstetr Gynecol 90(1):102–111Google Scholar
  21. 21.
    Leskosek B, Pajntar M (2002) Electromyography of the pregnant uterus in humans and sheep. 2nd European Medical & Biological Engineering Conference, vol. 4, no. 2, pp 544–545Google Scholar
  22. 22.
    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):365–473Google Scholar
  23. 23.
    Lucovnik M, Manver WL, Chambliss LR, Blumrick R, Balducci J, Novak-Antolic Z, Garfield RE (2011) Noninvasive uterine electromyography for prediction of preterm delivery. Am J Obstet Gynecol 204(3):228.e1Google Scholar
  24. 24.
    Lucovnik M, Novak-Antolic Z, Garfield RE (2012) Use of non-invasive uterine electromyography in the diagnosis of preterm labour. Facts Views & Vision in Obgyn 4(1):66–72Google Scholar
  25. 25.
    Alamedine D, Khalil M, Marque C (2013) Parameters extraction and monitoring in uterine EMG Signals. Detection of preterm deliveries. IRBM 34(4):322–325Google Scholar
  26. 26.
    Moslem B, Khalil M, Marque C, Diab M (2010) Energy distribution analysis of uterine electromyography signals. J Med Biol Eng 30(6):600Google Scholar
  27. 27.
    Arora S, Garg G (2012) A novel scheme to classify EHG signal for term and pre-term pregnancy analysis. International Journal of Computer Applications 51(18):37–41Google Scholar
  28. 28.
    Marque C, Terrien J, Rihana S, Germain G (2007) Preterm labour detection by use of a biophysical marker: the uterine electrical activity. BMC Pregnancy Childbirth 7(1):S5Google Scholar
  29. 29.
    Hussain AJ, Fergus P, Al-Askar H, Al-Jumeily D, Jager F, Jaafar A (2015) Dynamic neural network architecture inspired by the immune algorithm to predict preterm deliveries in pregnant women. Neurocomputing 151:963–974Google Scholar
  30. 30.
    Fergus P, Idowu I, Hussain A, Dobbins C (2016) Advanced artificial neural network classification for detecting preterm births using EHG records. Neurocomputing 188:42–49Google Scholar
  31. 31.
    de Lau H, Rabotti C, Bijloo R, Rooijakkers MJ, Mischi M, Oei SG (2013) Automated conduction velocity analysis in the electrohysterogram for prediction of imminent delivery: a preliminary study. Comput Math Methods Med 1–7Google Scholar
  32. 32.
    Rabotti C, Mischi M, Oei SG, Bergmans JWM (2010) Noninvasive estimation of the electrohysterographic action-potential conduction velocity. IEEE Trans Biomed Eng 57(9):2178–2187Google Scholar
  33. 33.
    Iams JD (2003) Prediction and early detection of preterm labor. Obstet Gynecol 101(2):402–412Google Scholar
  34. 34.
    Khalil M, Duchene J (2000) Uterine EMG analysis: a dynamic approach for change detection and classification. IEEE Trans Biomed Eng 47(6):748–756Google Scholar
  35. 35.
    Akay M (2000) Nonlinear biomedical signal processing. Wiley, HobokenGoogle Scholar
  36. 36.
    Park C, Looney D, Rehman N, Ahrabian A, Mandic DP (2013) Classification of motor imagery BCI using multivariate empirical mode decomposition. IEEE Trans Neural Syst Rehabil Eng 21(1):10–22Google Scholar
  37. 37.
    Sunan G, Han M, Hong X (2014) A fully automatic ocular artifact removal from EEG based on fourth-order tensor method. Biomed Eng Lett 4(1):55–63Google Scholar
  38. 38.
    Rabotti C, Mischi M, van Laar JO, Oei GS, Bergmans JW (2008) Estimation of internal uterine pressure by joint amplitude and frequency analysis of electrohysterographic signals. Physiol Meas 29(7):829–841Google Scholar
  39. 39.
    Diab MO, El-Merhie A, El-Halabi N, Khoder L (2010) Classification of uterine EMG signals using supervised classification method. J Biol Sci Eng 3(9):837–842Google Scholar
  40. 40.
    Vinken MPGC, Rabotti C, Mischi M, Oei OSG (2009) Accuracy of frequency-related parameters of the electrohysterogram for predicting preterm delivery: a review of the literature. Obstet Gynecol Surv 64(8):529–541Google Scholar
  41. 41.
    Terrien J, Germain G, Marque C, Karlsson B (2013) Bivariate piecewise stationary segmentation; improved pre-treatment for synchronization measures used on non-stationary biological signals. Med Eng Phys 35(8):1188–1196Google Scholar
  42. 42.
    Park C, Looney D, Kidmose P, Ungstrup M, Mandic DP (2011) Time-frequency analysis of EEG asymmetry using bivariate empirical mode decomposition. IEEE Trans Neural Syst Rehabil Eng 19(4):366–373Google Scholar
  43. 43.
    Salim L, Boukadoum M (2015) A weighted bio-signal denoising approach using empirical mode decomposition. Biomed Eng Lett 5(2):131–139Google Scholar
  44. 44.
    Huang NE, Shen Z, Long SR, Wu ML, Shih HH, Quanan Z, Yen NC, Tung CC, Liu HH (1998) The empirical mode decomposition and the hilbert spectrum for nonlinear and non-stationary time series analysis. Proc R Soc Lond A 454(1971):903–995MathSciNetzbMATHGoogle Scholar
  45. 45.
    Rehman N, Mandic DP (2011) Filter bank property of multivariate empirical mode decomposition. IEEE Trans Signal Process 59(5):2421–2426MathSciNetzbMATHGoogle Scholar
  46. 46.
    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):e0132116Google Scholar
  47. 47.
    Ryu J, Park C (2015) Time-frequency analysis of electrohysterogram for classification of term and preterm birth. IEIE Trans Smart Process Comput 4(2):103–109Google Scholar
  48. 48.
    Richman JS, Moorman JR (2000) Physiological time-series analysis using approximate entropy and sample entropy. Am J Physiol 278(6):2039–2049Google Scholar
  49. 49.
    Wu Z, Huang NE (2005) Ensemble empirical mode decomposition: a noise assisted data analysis method. Adv Adapt Data Anal 1(1):1–49Google Scholar
  50. 50.
    Pincus SM (1991) Approximate entropy as a measure of system complexity. Proc Natl Acad Sci USA 88(6):2297–2301MathSciNetzbMATHGoogle Scholar
  51. 51.
    Chawla N, Bowyer K, Hall L, Kegelmeyer W (2002) SMOTE: synthetic Minority Over-sampling Technique. J Artif Intell Res 16:321–357zbMATHGoogle Scholar
  52. 52.
    Witten IH, Frank E, Hall MA (2011) Data mining practical machine learning tools and techniques 3rd edition, ElsevierGoogle Scholar
  53. 53.
    Ho TK (1998) The random subspace method for constructing decision forests. IEEE Trans Pattern Anal Mach Intell 20(8):832–844Google Scholar
  54. 54.
    Breiman L (1994) Bagging predictors Technical Report. Department of Statistics University of California at BerkeleyGoogle Scholar
  55. 55.
    Chen M, Mandic DP (2008) Qualitative assessment of intrinsic mode functions of empirical mode decomposition. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp 1905–1908Google Scholar
  56. 56.
    Breiman L (2001) Random forests. Mach Learn 45(1):5–32zbMATHGoogle Scholar
  57. 57.
    Dill LV, Maiden RM, Engineer R (1946) The electrical potentials of the human uterus in labor. Am J Obstet Gynecol 52(5):735–745Google Scholar
  58. 58.
    Hon EH, Davis CD (1958) Cutaneous and uterine electrical potentials in labor—an experiment. Obstetrics Gynecology 12(1):47–53Google Scholar
  59. 59.
    Steer CM, Hertsch GJ (1950) Electrical activity of the human uterus in labor; the electrohysterograph. Am J Obstet Gynecol 59(1):25–40Google Scholar
  60. 60.
    Larks SD, Assali NS, Morton DG, Selle WA (1957) Electrical activity of the human uterus in labor. J Appl Physiol 10(3):479–483Google Scholar
  61. 61.
    Marque C, Duchene JMG, Leclercq S, Panczer GS, Chaumont J (1986) Uterine EHG processing for obstetrical monitoring. IEEE Trans Biomed Eng 12:1182–1187Google Scholar
  62. 62.
    Mansour S, Devedeux D, Germain G, Marque C, Duchene J (1996) Uterine EMG spectral analysis and relationship to mechanical activity in pregnant monkeys. Med Biol Eng Compu 34(2):115–121Google Scholar
  63. 63.
    Liang H, Lin Z, McCallum RW (2000) Artifact reduction in electrogastrogram based on empirical mode decomposition method. Med Biol Eng Compu 38(1):35–41Google Scholar
  64. 64.
    Cuzick J (1985) A wilcoxon-type test for trend. Stat Med 4(4):543–547Google Scholar
  65. 65.
    Manis G (2008) Fast computation of approximate entropy. Comput Methods Programs Biomed 91(1):48–54Google Scholar
  66. 66.
    Pan YH, Wang YH, Liang SF, Lee KT (2011) Fast computation of sample entropy and approximate entropy in biomedicine. Comput Methods Programs Biomed 104(3):382–396Google Scholar
  67. 67.
    Manis G, Aktaruzzaman M, Sassi R (2018) Low computational cost for sample entropy. Entropy 20(1):61Google Scholar
  68. 68.
    Wang YH, Yeh CH, Young HWV, Hu K, Lo MT (2014) On the computational complexity of the empirical mode decomposition algorithm. Phys A 400:159–167Google Scholar
  69. 69.
    Eftekhar A, Toumazou C, Drakakis EM (2013) Empirical mode decomposition: real-time implementation and applications. J Signal Process Syst 73(1):43–58Google Scholar
  70. 70.
    Santillan-Guzman A, Fischer M, Heute U, Schmidt G (2013) Real-time empirical mode decomposition for EEG signal enhancement. In: Proceedings of the 21st European Signal Processing Conference (EUSIPCO), pp 1–5Google Scholar
  71. 71.
    Chang LW, Lo MT, Anssari N, Hsu KH, Huang NE, Wen-mei WH (2011) Parallel implementation of multi-dimensional ensemble empirical mode decomposition. IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 1621–1624Google Scholar
  72. 72.
    Chen PY, Lai YC, Zheng JY (2016) Hardware design and implementation for empirical mode decomposition. IEEE Trans Industr Electron 63(6):3686–3694Google Scholar
  73. 73.
    Hong YY, Bao YQ (2012) FPGA implementation for real-time empirical mode decomposition. IEEE Trans Instrum Meas 61(12):3175–3184MathSciNetGoogle Scholar

Copyright information

© The Korean Institute of Electrical Engineers 2019

Authors and Affiliations

  • Jiwoo You
    • 1
    • 2
  • Youngjoo Kim
    • 1
    • 2
  • Woojoon Seok
    • 1
  • Seungmin Lee
    • 3
  • Donggyu Sim
    • 1
  • Kwang Suk Park
    • 4
  • Cheolsoo Park
    • 1
    Email author
  1. 1.Department of Computer EngineeringKwangwoon UniversitySeoulKorea
  2. 2.Faculty of Science and EngineeringRijksuniversiteit GroningenGroningenThe Netherlands
  3. 3.School of Electrical Engineering, College of Creative EngineeringKookmin UniversitySeoulKorea
  4. 4.Department of Biomedical Engineering, College of MedicineSeoul National UniversitySeoulKorea

Personalised recommendations