Automated detection of preterm condition using uterine electromyography based topological features

• Autorzy: Vinothini S. , Punitha N. , Karthick P.A. , Ramakrishnan S.

Identyfikatory

DOI

10.1016/j.bbe.2021.01.004

• Języki publikacji: EN

Abstrakty

EN

Accurate prediction of preterm birth is a global, public health priority. This necessitates the need for an efficient technique that aids in early diagnosis. The objective of this study is to develop an automated system for an effective detection of preterm (weeks of gestation < 37) condition using Electrohysterography (EHG) and topological features associated with the frequency components of signals. The EHG signals recorded prior to gestational age of 26 weeks are considered. The pre-processed signals are subjected to discrete Fourier transform to obtain the Fourier coefficients. The envelope is computed from the boundary of the complex Fourier coefficients identified using the a-shape method. Topological features namely, area, perimeter, circularity, convexity, ellipse variance and bending energy are extracted from the envelope. Classifications based on threshold-determination method and machine learning algorithms namely, naïve Bayes, decision tree and random forest are employed to differentiate the term and preterm conditions. The results show that the Fourier coefficients of EHG signals exhibit different shapes in the term and preterm conditions. The regularity of signals is found to increase in preterm condition. All the features are found to have significant differences between these two conditions. Bending energy as a single biomarker achieves a maximum accuracy of 80.7%. The random forest model based on the topological features detects the conditions with the maximum accuracy and positive predictive value of about 98.6%. Therefore, the proposed automated system seems to be effective and could be used for the accurate detection of term and preterm conditions.

Słowa kluczowe

EN

term condition; preterm condition; electrohysterography; discrete Fourier transform; topological features

PL

stan przedwczesny; elektrohisterografia; transformacja Fouriera dyskretna; cechy topologiczne

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2021
• Tom: Vol. 41, no. 1
• Strony: 293--305
• Opis fizyczny: Bibliogr. 59 poz., rys., tab., wykr.

Twórcy

autor

Vinothini S.

• Non-Invasive Imaging and Diagnostics Laboratory, Biomedical Engineering Group, Department of Applied Mechanics, Indian Institute of Technology, Madras 600036, India

autor

Punitha N.

• Non-Invasive Imaging and Diagnostics Laboratory, Biomedical Engineering Group, Department of Applied Mechanics, Indian Institute of Technology Madras, Chennai, India

autor

Karthick P.A.

• Department of Instrumentation and Control Engineering, National Institute of Technology Tiruchirappalli, Tiruchirappalli, India

autor

Ramakrishnan S.

• Non-Invasive Imaging and Diagnostics Laboratory, Biomedical Engineering Group, Department of Applied Mechanics, Indian Institute of Technology Madras, Chennai, India

Bibliografia

• [1] FIGO Working Group on Good Clinical Practice in Maternal–Fetal Medicine, Di Renzo GC, Fonseca E, Gratacos E, Hassan S, Kurtser M, et al. Good clinical practice advice: prediction of preterm labor and preterm premature rupture of membranes. Int J Gynecol Obstet 2019;144(3):340–6.
• [2] Zhu YZ, Peng GQ, Tian GX, Qu XL, Xiao SY. New model for predicting preterm delivery during the second trimester of pregnancy. Sci Rep 2017;7(1):1–9.
• [3] Shafik A. Electrohysterogram: study of the electromechanical activity of the uterus in humans. Eur J Obstet Gynecol Reprod Biol 1997;73(1):85–9.
• [4] Gao P, Hao D, An Y, Wang Y, Qiu Q, Yang L, et al. Comparison of electrohysterogram signal measured by surface electrodes with different designs: a computational study with dipole band and abdomen models. Sci Rep 2017;7(1):1–10.
• [5] Punitha N, Ramakrishnan S. Analysis of uterine EMG signals in term and preterm conditions using generalised Hurst exponent features. Electron Lett 2019;55(12):681–3.
• [6] Maul H, Maner WL, Olson G, Saade GR, Garfield RE. Non-invasive transabdominal uterine electromyography correlates with the strength of intrauterine pressure and is predictive of labor and delivery. J Matern-Fetal Neo M 2004;15(5):297–301.
• [7] Lucovnik M, Kuon RJ, Chambliss LR, Maner WL, Shi SQ, Shi L, et al. Use of uterine electromyography to diagnose term and preterm labor. Acta Obstet Gynecol Scand 2011;90 (2):150–7.
• [8] Chen Y, Hao Y. Feature extraction and classification of EHG between pregnancy and labour group using Hilbert-Huang transform and extreme learning machine. Comput Math Method M 2017;20177949507.
• [9] Sadi-Ahmed N, Kacha B, Taleb H, Kedir-Talha M. Relevant features selection for automatic prediction of preterm deliveries from pregnancy electrohysterograhic (EHG) records. J Med Syst 2017;41(12):204.
• [10] Peng J, Hao D, Yang L, Du M, Song X, Jiang H, et al. Evaluation of electrohysterogram measured from different gestational weeks for recognizing preterm delivery: a preliminary study using random Forest. Biocybern Biomed Eng 2020;40(1):352–62.
• [11] Garcia-Casado J, Ye-Lin Y, Prats-Boluda G, Mas-Cabo J, Alberola-Rubio J, Perales A. Electrohysterography in the diagnosis of preterm birth: a review. Physiol Meas 2018;39 (2):02TR01.
• [12] Fele-Žorž G, Kavšek G, Novak-Antolic Ž, Jager F. 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 2008;46(9):911–22.
• [13] Ahmed MU, Chanwimalueang T, Thayyil S, Mandic DP. A multivariate multiscale fuzzy entropy algorithm with application to uterine EMG complexity analysis. Entropy 2017;19(1):2.
• [14] Hassan M, Terrien J, Marque C, Karlsson B. Comparison between approximate entropy, correntropy and time reversibility: application to uterine electromyogram signals. Med Eng Phys 2011;33(8):980–6.
• [15] Diab A, Hassan M, Marque C, Karlsson B. Quantitative performance analysis of four methods of evaluating signal nonlinearity: application to uterine EMG signals. Proc. 2012 IEEE EMBS; 2012.
• [16] Rabotti C, Mischi M. Propagation of electrical activity in uterine muscle during pregnancy: a review. Acta Physiol (Oxf) 2015;213(2):406–16.
• [17] Lange L, Vaeggemose A, Kidmose P, Mikkelsen E, Uldbjerg N, Johansen P. Velocity and directionality of the electrohysterographic signal propagation. PLoS One 2014;9(1):e86775.
• [18] Zhang Z, Song Y, Cui H, Wu J, Schwartz F, Qi H. Topological analysis and gaussian decision tree: effective representation and classification of biosignals of small sample size. IEEE Trans Biomed Eng 2016;64(9):2288–99.
• [19] Lashkari S, Sheikhani A, Golpayegani MRH, Moghimi A, Kobravi HR. Topological feature extraction of nonlinear signals and trajectories and its application in EEG signals classification. Turk J Electr Eng Comput Sci 2018;26 (3):1329–42.
• [20] Lashkari S, Sheikhani A, Golpayegani MRH, Moghimi A, Kobravi H. Detection and prediction of absence seizures based on nonlinear analysis of the EEG in Wag/Rij animal model. ICNSJ 2018;5(1):21–7.
• [21] Phinyomark A, Ibáñez-Marcelo E, Petri G. Signal processing and machine learning for biomedical big data. Boca Raton: CRC; 2018 [chapter 11].
• [22] Jero SE, Bharathi KD, Ramakrishnan S. A method to differentiate fatiguing conditions in surface electromyography signals using instantaneous spectral centroid. Proc. IEEE EMBS; 2020.
• [23] Goldberger AL, Amaral LA, Glass L, Hausdorff JM, Ivanov PC, Mark RG, et al. Physiobank, Physiotoolkit , and Physionet: components of a new research resource for complex physiological signals. Circulation 2000;101(23):e215–20.
• [24] Lyons RG. Understanding digital signal processing. 3rd ed. England: Prentice Hall; 2004.
• [25] Edelsbrunner H, Kirkpatrick D, Seidel R. On the shape of a set of points in the plane. IEEE Trans Inf Theory 1983;29 (4):551–9.
• [26] Burger WM, Burge J. Digital image processing: an algorithmic introduction using java. 1st ed. England: SSBM; 2008.
• [27] Mingqiang Y, Kidiyo K, Joseph R. A survey of shape feature extraction techniques. Pattern Recognit 2008;15(7):43–90.
• [28] Chaki J, Dey N. A beginner's guide to image shape feature extraction techniques. 1st ed. Boca Raton: CRC press; 2019.
• [29] da Fona Costa L, Cesar Jr RM. Shape classification and analysis: theory and practice. 2nd ed. Boca Raton: CRC Press; 2009.
• [30] Young IT, Walker JE, Bowie JE. An analysis technique for biological shape I. Inf Control 1974;25(4):357–70.
• [31] Acharya UR, Sudarshan VK, Rong SQ, Tan Z, Lim CM, Koh JE, et al. Automated detection of premature delivery using empirical mode and wavelet packet decomposition techniques with uterine electromyogram signals. Comput Bio Med 2017;85:33–42.
• [32] He H, Bai Y, Garcia EA, Li S. ADASYN: adaptive synthetic sampling approach for imbalanced learning. Proc. 2008 IJCNN; 2008.
• [33] Tharwat A. Classification assessment methods. Appl Comput Inform 2020. http://dx.doi.org/10.1016/j.aci.2018.08.003. 2634-1964.
• [34] Fawcett T. An introduction to ROC analysis. Pattern Recognit 2006;27(8):861–74.
• [35] Hao D, Qiu Q, Zhou X, An Y, Peng J, Yang L, et al. Application of decision tree in determining the importance of surface electrohysterography signal characteristics for recognizing uterine contractions. Biocybern Biomed Eng 2019;39(3):806–13.
• [36] Garfield RE, Maner WL. Physiology and electrical activity of uterine contractions. Semin Cell Dev Biol 2007;18(3):289–95.
• [37] Mischi M, Chen C, Ignatenko T, de Lau H, Ding B, Oei SG, et al. Dedicated entropy measures for early assessment of pregnancy progression from single channel electrohysterography. IEEE Trans Biomed Eng 2017;65 (4):875–84.
• [38] Buhimschi C, Boyle MB, Garfield RE. Electrical activity of the human uterus during pregnancy as recorded from the abdominal surface. Obstet Gynecol 1997;90(1):102–11.
• [39] Sammali F, Kuijsters NPM, Schoot BC, Mischi M, Rabotti C. Feasibility of transabdominal electrohysterography for analysis of uterine activity in nonpregnant women. Reprod Sci 2018;25(7):1124–33.
• [40] Kissler KJ, Lowe NK, Hernandez TL. An integrated review of uterine activity monitoring for evaluating labor dystocia. J Midwifery Womens Health 2020;65(3):323–34.
• [41] Saleem S, Saeed A, Usman S, Ferzund J, Arshad J, Mirza J, et al. Granger causal analysis of electrohysterographic and tocographic recordings for classification of term vs. Preterm births. Biocybern Biomed Eng 2020;40(1):454–67.
• [42] Chen L, Hao Y, Hu X. Detection of preterm birth in electrohysterogram signals based on wavelet transform and stacked sparse autoencoder. PLoS One 2019;14(4): e0214712.
• [43] Hao D, An Y, Qiao X, Qiu Q, Zhou X, Peng J. Development of electrohysterogram recording system for monitoring uterine contraction. J Healthc Eng 2019;20194230157.
• [44] Horoba K, Wrobel J, Jezewski J, Kupka T, Roj D, Jezewski M. Automated detection of uterine contractions in tocography signals–comparison of algorithms. Biocybern Biomed Eng 2016;36(4):610–8.
• [45] Lucovnik M, Novak-Antolic Z, Garfield RE. Use of non-invasive uterine electromyography in the diagnosis of preterm labour. Facts Views Vis Obgyn 2012;4(1):66.
• [46] Muszynski C, Happillon T, Azudin K, Tylcz JB, Istrate D, Marque C. Automated electrohysterographic detection of uterine contractions for monitoring of pregnancy: feasibility and prospects. BMC Pregnancy Childbirth 2018;18 (1):1–8.
• [47] Esgalhado F, Batista AG, Mouriño H, Russo S, Dos Reis CRP, Serrano F, et al. Uterine contractions clustering based on electrohysterography. Comput Biol Med 2020;123103897.
• [48] Esgalhado F, Batista AG, Mouriño H, Russo S, dos Reis CRP, Serrano F, et al. Automatic contraction detection using uterine electromyography. Appl Sci 2020;10(20):7014.
• [49] Hao D, Peng J, Wang Y, Liu J, Zhou X, Zheng D. Evaluation of convolutional neural network for recognizing uterine contractions with electrohysterogram. Comput Biol Med 2019;113103394.
• [50] Ryu J, Park C. Time-frequency analysis of electrohysterogram for classification of term and preterm birth. IEIE SPC 2015;4(2):103–9.
• [51] Fergus P, Idowu I, Hussain A, Dobbins C. Advanced artificial neural network classification for detecting preterm births using EHG records. Neurocomputing 2016;188:42–9.
• [52] Hoseinzadeh S, Amirani MC. Use of electro hysterogram (EHG) signal to diagnose preterm birth. Proc. ICEE; 2018.
• [53] Jager F, Libenšek S, Geršak K. Characterization and automatic classification of preterm and term uterine records. PLoS One 2018;13(8):e0202125.
• [54] Despotović D, Zec A, Mladenovic´ K, Radin N, Turukalo TL. A machine learning approach for an early prediction of preterm delivery. Proc. SISY; 2018.
• [55] Hemthanon C, Janjarasjitt S. Examination of time- domain features of EHG data for preterm-term birth classification. J Comput 2019;30(2):41–54.
• [56] Hasan I, Das A, Imamul M, Bhuiyan H. Nonlinear temporal analysis of uterine EMG for preterm birth classification. Proc. IC4ME2; 2019.
• [57] Peng J, Hao D, Yang L, Du M, Song X, Jiang H, et al. Evaluation of electrohysterogram measured from different gestational weeks for recognizing preterm delivery: a preliminary study using random Forest. Biocybern Biomed Eng 2020;40(1):352–62.
• [58] Verdenik I, Pajntar M, Leskošek B. Uterine electrical activity as predictor of preterm birth in women with preterm contractions. Eur J Obstet Gynecol Reprod Biol 2001;95 (2):149–53.
• [59] Vinken MP, Rabotti C, Mischi M, Oei SG. Accuracy of frequency-related parameters of the electrohysterogram for predicting preterm delivery: a review of the literature. Obstet Gynecol Surv 2009;64(8):529–41.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).