Advertisement

Prediction of intrapartum fetal hypoxia considering feature selection algorithms and machine learning models

  • Zafer Cömert
  • Abdulkadir Şengür
  • Ümit BudakEmail author
  • Adnan Fatih Kocamaz
Research
Part of the following topical collections:
  1. Special Issue on Artificial Intelligence in Health Informatics

Abstract

Introduction

Cardiotocography (CTG) consists of two biophysical signals that are fetal heart rate (FHR) and uterine contraction (UC). In this research area, the computerized systems are usually utilized to provide more objective and repeatable results.

Materials and Methods

Feature selection algorithms are of great importance regarding the computerized systems to not only reduce the dimension of feature set but also to reveal the most relevant features without losing too much information. In this paper, three filters and two wrappers feature selection methods and machine learning models, which are artificial neural network (ANN), k-nearest neighbor (kNN), decision tree (DT), and support vector machine (SVM), are evaluated on a high dimensional feature set obtained from an open-access CTU-UHB intrapartum CTG database. The signals are divided into two classes as normal and hypoxic considering umbilical artery pH value (pH < 7.20) measured after delivery. A comprehensive diagnostic feature set forming the features obtained from morphological, linear, nonlinear, time–frequency and image-based time–frequency domains is generated first. Then, combinations of the feature selection algorithms and machine learning models are evaluated to achieve the most effective features as well as high classification performance.

Results

The experimental results show that it is possible to achieve better classification performance using lower dimensional feature set that comprises of more related features, instead of the high-dimensional feature set. The most informative feature subset was generated by considering the frequency of selection of the features by feature selection algorithms. As a result, the most efficient results were produced by selected only 12 relevant features instead of a full feature set consisting of 30 diagnostic indices and SVM model. Sensitivity and specificity were achieved as 77.40% and 93.86%, respectively.

Conclusion

Consequently, the evaluation of multiple feature selection algorithms resulted in achieving the best results.

Keywords

Biomedical signal processing Fetal heart rate Feature selection Classification Machine learning 

Notes

Acknowledgements

We would like to thanks to Dr. Sami Güngör due to its comments on the medical background.

Funding

There is no funding source for this article.

Compliance with ethical standards

Conflicts of interest

The authors declare that there is no conflict to interest related to this paper.

Ethical approval

This article does not contain any data, or other information from studies or experimentation, with the involvement of human or animal subjects.

Supplementary material

13755_2019_79_MOESM1_ESM.docx (356 kb)
Supplementary material 1 (DOCX 357 kb)

References

  1. 1.
    Grivell RM, Alfirevic Z, Gyte GM, Devane D. Antenatal cardiotocography for fetal assessment. Cochrane Database Syst Rev. 2010;9:1–48.  https://doi.org/10.1002/14651858.CD007863.pub2.CrossRefGoogle Scholar
  2. 2.
    Strachan BK, Sahota DS, Van Wijngaarden WJ, James DK, Chang AMZ. Computerised analysis of the fetal heart rate and relation to acidaemia at delivery. Br J Obstet Gynaecol. 2001;108:848–52.  https://doi.org/10.1016/S0306-5456(00)00195-9.CrossRefGoogle Scholar
  3. 3.
    Pinas A, Chandraharan E. Continuous cardiotocography during labour: analysis, classification and management. Best Pract. Res. Clin. Obstet. Gynaecol. 2016;30:33–47.  https://doi.org/10.1016/j.bpobgyn.2015.03.022.CrossRefGoogle Scholar
  4. 4.
    Norén H, Amer-Wåhlin I, Hagberg H, Herbst A, Kjellmer I, Marşál K, Olofsson P, Rosén KG. Fetal electrocardiography in labor and neonatal outcome: data from the Swedish randomized controlled trial on intrapartum fetal monitoring. Am J Obstet Gynecol. 2017;188:183–92.  https://doi.org/10.1067/mob.2003.109.CrossRefGoogle Scholar
  5. 5.
    Georgoulas G, Karvelis P, Spilka J, Chudáček V, Stylios CD, Lhotská L. Investigating pH based evaluation of fetal heart rate (FHR) recordings. Health Technol. (Berl). 2017;7:241–54.  https://doi.org/10.1007/s12553-017-0201-7.CrossRefGoogle Scholar
  6. 6.
    Bernardes J, Costa-Pereira A, Ayres-De-Campos D, Van Geijn HP, Pereira-Leite L. Evaluation of interobserver agreement of cardiotocograms. Int. J. Gynecol. Obstet. 1997;57:33–7.  https://doi.org/10.1016/S0020-7292(97)02846-4.CrossRefGoogle Scholar
  7. 7.
    Donker DK, van Geijn HP, Hasman A. Interobserver variation in the assessment of fetal heart rate recordings. Eur J Obstet Gynecol Reprod Biol. 1993;52:21–8.  https://doi.org/10.1016/0028-2243(93)90220-7.CrossRefGoogle Scholar
  8. 8.
    Czabanski R, Jezewski J, Matonia A, Jezewski M. Computerized analysis of fetal heart rate signals as the predictor of neonatal acidemia. Expert Syst Appl. 2012;39:11846–60.  https://doi.org/10.1016/j.eswa.2012.01.196.CrossRefGoogle Scholar
  9. 9.
    Ayres-de-Campos D, Spong CY, Chandraharan E. FIGO consensus guidelines on intrapartum fetal monitoring: cardiotocography. Int. J. Gynecol. Obstet. 2015;131:13–24.  https://doi.org/10.1016/j.ijgo.2015.06.020.CrossRefGoogle Scholar
  10. 10.
    Rhose S, Heinis AMF, Vandenbussche F, van Drongelen J, van Dillen J. Inter- and intra-observer agreement of non-reassuring cardiotocography analysis and subsequent clinical management. Acta Obstet Gynecol Scand. 2014;93:596–602.  https://doi.org/10.1111/aogs.12371.CrossRefGoogle Scholar
  11. 11.
    Ayres-de-Campos D, Ugwumadu A, Banfield P, Lynch P, Amin P, Horwell D, Costa A, Santos C, Bernardes J, Rosen K. A randomised clinical trial of intrapartum fetal monitoring with computer analysis and alerts versus previously available monitoring. BMC Pregnancy Childbirth. 2010;10:71.  https://doi.org/10.1186/1471-2393-10-71.CrossRefGoogle Scholar
  12. 12.
    Zhao Z, Zhang Y, Comert Z, Deng Y. Computer-aided diagnosis system of fetal hypoxia incorporating recurrence plot with convolutional neural network. Front. Physiol. 2019;10:255.  https://doi.org/10.3389/fphys.2019.00255.CrossRefGoogle Scholar
  13. 13.
    Signorini MG, Magenes G, Cerutti S, Arduini D. Linear and nonlinear parameters for the analysis of fetal heart rate signal from cardiotocographic recordings. IEEE Trans Biomed Eng. 2003;50:365–74.  https://doi.org/10.1109/TBME.2003.808824.CrossRefGoogle Scholar
  14. 14.
    Karin J, Hirsch M, Sagiv C, Akselrod S. Fetal autonomic nervous system activity monitoring by spectral analysis of heart rate variations. In: Proceedings of computers in cardiology; 1992. p. 479–482.  https://doi.org/10.1109/cic.1992.269517.
  15. 15.
    Zarmehri MN, Castro L, Santos J, Bernardes J, Costa A, Santos CC. On the prediction of foetal acidaemia: a spectral analysis-based approach. Comput Biol Med. 2019;109:235–41.  https://doi.org/10.1016/j.compbiomed.2019.04.041 CrossRefGoogle Scholar
  16. 16.
    Romagnoli S, Sbrollini A, Burattini L, Marcantoni I, Morettini M, Burattini L. Digital cardiotocography: what is the optimal sampling frequency? Biomed Signal Process Control. 2019;51:210–5.  https://doi.org/10.1016/j.bspc.2019.02.016.CrossRefGoogle Scholar
  17. 17.
    Cömert Z, Kocamaz AF. Cardiotocography analysis based on segmentation-based fractal texture decomposition and extreme learning machine. In: 25th Signal processing and communications applications conference; 2017. p. 1–4.  https://doi.org/10.1109/siu.2017.7960397.
  18. 18.
    Cömert Z, Kocamaz AF, Subha V. Prognostic model based on image-based time–frequency features and genetic algorithm for fetal hypoxia assessment. Comput Biol Med. 2018.  https://doi.org/10.1016/j.compbiomed.2018.06.003.CrossRefGoogle Scholar
  19. 19.
    Cömert Z, Kocamaz AF. A study based on gray level co-occurrence matrix and neural network community for determination of hypoxic fetuses. In: International artificial intelligence and data processing symposium, TR, 2016. p. 569–573.  https://doi.org/10.13140/rg.2.2.23901.00489.
  20. 20.
    Usha Sri A, Malini M, Chandana G. Feature extraction of cardiotocography signal. In: Satapathy SC, Raju KS, Shyamala K, Krishna DR, Favorskaya MN, editors. Advances in decision sciences, image processing, security and computer vision. Cham: Springer; 2020. p. 74–81.Google Scholar
  21. 21.
    Alkhasawneh MS. Hybrid cascade forward neural network with elman neural network for disease prediction. Arab J Sci. Eng. 2019.  https://doi.org/10.1007/s13369-019-03829-3.CrossRefGoogle Scholar
  22. 22.
    Cömert Z, Kocamaz AF. Evaluation of fetal distress diagnosis during delivery stages based on linear and nonlinear features of fetal heart rate for neural network community. Int J Comput Appl. 2016;156:26–31.  https://doi.org/10.5120/ijca2016912417.CrossRefGoogle Scholar
  23. 23.
    Alsayyari A. Fetal cardiotocography monitoring using Legendre neural networks. Biomed. Eng. Tech. 2019;100000:10000.  https://doi.org/10.1515/bmt-2018-0074.CrossRefGoogle Scholar
  24. 24.
    Uzun A, Kızıltas CE, Yılmaz E. Cardiotocography data set classification with extreme learning machine. In: International conference on advanced technologies, computer engineering and science; 2018. p. 224–230.Google Scholar
  25. 25.
    Cömert Z, Kocamaz AF. Comparison of machine learning techniques for fetal heart rate classification. Acta Phys Pol, A. 2017;132:451–4.  https://doi.org/10.12693/aphyspola.131.451.CrossRefGoogle Scholar
  26. 26.
    Stylios CD, Georgoulas G, Karvelis P, Spilka J, Chudáček V, Lhotska L. Least squares support vector machines for FHR classification and assessing the pH based categorization. In: Kyriacou E, Christofides S, Pattichis CS, editors. XIV Mediterranean conference on medical and biological engineering and computing, 2016 (MEDICON 2016), 31 March–2 April 2016, Paphos, Cyprus. Cham: Springer; 2016. p. 1211–1215.  https://doi.org/10.1007/978-3-319-32703-7_234.CrossRefGoogle Scholar
  27. 27.
    Spilka J, Frecon J, Leonarduzzi R, Pustelnik N, Abry P, Doret M. Sparse support vector machine for intrapartum fetal heart rate classification. IEEE J. Biomed. Heal. Inform. 2016;10000:10000.  https://doi.org/10.1109/JBHI.2016.2546312.CrossRefGoogle Scholar
  28. 28.
    Xu L, Georgieva A, Redman CWG, Payne SJ. Feature selection for computerized fetal heart rate analysis using genetic algorithms. In: 2013 35th Annual international conference of the IEEE Engineering in Medicine and Biology Society; 2013. pp. 445–448.  https://doi.org/10.1109/embc.2013.6609532.
  29. 29.
    Cömert Z, Kocamaz AF. Novel software for comprehensive analysis of cardiotocography signals CTG-OAS. In: Karci A, editor. International conference on artificial intelligence and data processing. Malatya: IEEE; 2017. p. 1–6.  https://doi.org/10.1109/idap.2017.8090210.
  30. 30.
    Chudacek V, Spilka J, Rubackova B, Koucky M, Georgoulas G, Lhotska L, Stylios C. Evaluation of feature subsets for classification of cardiotocographic recordings. In: 35th Annual conference on computers in cardiology 2008. Piscataway, NJ: IEEE; 2008. p. 845–848.  https://doi.org/10.1109/cic.2008.4749174.
  31. 31.
    Menai MEB, Mohder FJ. Al-mutairi, Influence of feature selection on naïve Bayes classifier for recognizing patterns in cardiotocograms. J. Med. Bioeng. 2013;2:66–70.  https://doi.org/10.12720/jomb.2.1.66-70.CrossRefGoogle Scholar
  32. 32.
    Chudáček V, Spilka J, Burša M, Janků P, Hruban L, Huptych M, Lhotská L. Open access intrapartum CTG database. BMC Pregnancy Childbirth. 2014;14:16.  https://doi.org/10.1186/1471-2393-14-16.CrossRefGoogle Scholar
  33. 33.
    Gonçalves H, Bernardes J, Paula Rocha A, Ayres-de-Campos D. Linear and nonlinear analysis of heart rate patterns associated with fetal behavioral states in the antepartum period. Early Hum Dev. 2007;83:585–91.  https://doi.org/10.1016/j.earlhumdev.2006.12.006.CrossRefGoogle Scholar
  34. 34.
    Spilka J, Chudáček V, Koucký M, Lhotská L, Huptych M, Janků P, Georgoulas G, Stylios C. Using nonlinear features for fetal heart rate classification. Biomed Signal Process Control. 2012;7:350–7.  https://doi.org/10.1016/j.bspc.2011.06.008.CrossRefGoogle Scholar
  35. 35.
    Huang M-L, Yung-Yan H. Fetal distress prediction using discriminant analysis, decision tree, and artificial neural network. J. Biomed. Sci. Eng. 2012;05:526–33.  https://doi.org/10.4236/jbise.2012.59065.CrossRefGoogle Scholar
  36. 36.
    Sahin H, Subasi A. Classification of the cardiotocogram data for anticipation of fetal risks using machine learning techniques. Appl. Soft Comput. 2015;33:231–8.  https://doi.org/10.1016/j.asoc.2015.04.038.CrossRefGoogle Scholar
  37. 37.
    Aha DW, Kibler D, Albert MK. Instance-based learning algorithms. Mach. Learn. 1991;6:37–66.  https://doi.org/10.1007/BF00153759.CrossRefGoogle Scholar
  38. 38.
    Akbulut Y, Sengur A, Guo Y, Smarandache F. NS-k-NN: neutrosophic set-based k-nearest neighbors classifier. Symmetry (Basel). 2017;9:179.CrossRefGoogle Scholar
  39. 39.
    Safavian SR, Landgrebe D. A survey of decision tree classifier methodology. IEEE Trans. Syst. Man. Cybern. 1991;21:660–74.MathSciNetCrossRefGoogle Scholar
  40. 40.
    Altuntaş Y, Kocamaz AF, Cömert Z, Cengiz R, Esmeray M. Identification of haploid maize seeds using gray level co-occurrence matrix and machine learning techniques. In: 2018 International conference on artificial intelligence and data Processing, Malatya, Turkey; 2018. p. 1–5.  https://doi.org/10.1109/idap.2018.8620740
  41. 41.
    Cömert Z, Kocamaz AF. Fetal hypoxia detection based on deep convolutional neural network with transfer learning approach. In: Silhavy R, editor. Software engineering and algorithms in intelligent systems. Cham: Springer; 2019. p. 239–248.  https://doi.org/10.1007/978-3-319-91186-1_25.Google Scholar
  42. 42.
    Subha V, Murugan D, Boopathi AM, Velappan S, Murugan D, Boopathi M. A hybrid filter-wrapper attribute reduction approach for fetal risk anticipation. Asian J. Res. Soc. Sci. Humanit. 2017;7:1094–106.Google Scholar
  43. 43.
    Velappan S, Murugan D, Prabha S, Boopathi M. Genetic Algorithm based feature subset selection for fetal state classification. J. Commun. Technol. Electron. Comput. Sci. 2015;2:13–7.CrossRefGoogle Scholar
  44. 44.
    Ayres-de-campos D, Bernardes J, Garrido A, Marques-de-sá J, Pereira-leite L. SisPorto 2.0: a program for automated analysis of cardiotocograms. J. Matern. Fetal. Med. 2000;9:311–8.  https://doi.org/10.3109/14767050009053454.CrossRefGoogle Scholar
  45. 45.
    Spilka J, Georgoulas G, Karvelis P, Oikonomou VP, Chudáček V, Stylios C, Lhotská L, Jankru P. Automatic evaluation of FHR recordings from CTU-UHB CTG database. In: Bursa M, Khuri S, Renda ME, editors. Proceedings of 4th international conference on information technology in bio- and medical informatics (ITBAM 2013), Prague, Czech Republic, 28 August 2013. Berlin: Springer, 2013, pp. 47–61.  https://doi.org/10.1007/978-3-642-40093-3_4.CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Department of Software EngineeringSamsun UniversitySamsunTurkey
  2. 2.Department of Electrical and Electronics Engineering, Technology FacultyFirat UniversityElazigTurkey
  3. 3.Department of Electrical and Electronics EngineeringBitlis Eren UniversityBitlisTurkey
  4. 4.Department of Computer Engineeringİnönü UniversityMalatyaTurkey

Personalised recommendations