Abstract
Intrauterine fetal hypoxia is one of the leading cause of perinatal mortality and morbidity. This can eventually lead to severe neurological damage like cerebral palsy and in extreme cases to fetal demise. It is thus necessary to monitor the fetus during intrapartum and antepartum period. Cardiotocograph (CTG) as a method of assessing the status of the fetus had been in use for last six decades. Nowadays it is the most widely used non-invasive technique for the continuous monitoring of the fetal heart rate (FHR) and the uterine contraction pressure (UCP). Though its introduction limited the birth related problems, the accuracy of interpretation was hindered by quite a few factors. Different guidelines that are provided for the interpretation are based on crisp logic which fails to capture the inherent uncertainty present in the medical diagnosis. Misinterpretations had led to inaccurate diagnosis which resulted in many medico-legal litigations. The vagueness present in the physician’s evaluation is best modeled using soft-computing based techniques. In this paper authors used the CTG dataset from UCI Irvine Machine Learning Data Repository which contains 2126 data and each data-point is represented by 37 features. Dimensionality of the feature set was reduced using different automated methods as well as manually by the physicians. The resulting data sets were classified using various machine learning algorithms. Aim of this study is to establish which set of features is best suited to give good insight into the status of the fetus and also determine the most effective machine learning technique for this purpose. The accuracy of the outcomes were measured using statistical methods such as sensitivity, specificity, precision, F-Measure, confusion matrix and kappa value. We obtained an accuracy of 99.91% and kappa measure of 0.997 when the feature set was reduced using MRMR.
Similar content being viewed by others
References
Alonso-Betanzos A, Guijarro-Berdiñas B, Moret-Bonillo V, López-Gonzalez S (1995) The NST-EXPERT project: the need to evolve. J Artif Intell Med 7(4):297–313
Barber DC, Howlett PJ, Smart R (1975) Principal component analysis in medical research. J Appl Stat 2(1):39–43
Barquero-Pérez Ó, Santiago-Mozos R, Lillo-Castellano JM, García-Viruete B, Goya-Esteban R, Caamaño AJ, Rojo-Álvarez JL, Martín-Caballero C et al (2017) Fetal heart rate analysis for automatic detection of perinatal hypoxia using normalized compression distance and machine learning. Front Physiol 8:113. https://doi.org/10.3389/fphys.2017.00113
Cömert Z, Kocamaz AF (2018) Fetal hypoxia detection based on deep convolutional neural network with transfer learning approach. Springer series on chemical sensors and biosensors 239–248.
Das, S., Roy, K., Saha, C.K. (2013) Application of FURIA in the classification of cardiotocograph. In: IEEE- International Conference on Research and Development Prospects on Engineering and Technology, pp. 120–124. IEEE Press, Chennai
Das S, Roy K, Saha C K (2017) A linear time series analysis of fetal heart rate to detect the variability: measures using cardiotocography. In: Bhattacharyya S, Das N, Bhattacharyya D, Mukherjee A (ed). Handbook of research on recent developments in intelligent communication application, vol. 1. IGI Global, pp 471–495.
Dawes GS, Visser GH, Goodman JD, Redman CW (1981) Numerical analysis of the human fetal heart rate: the quality of ultrasound records. Am J Obstet Gynecol 141(1):43–52
De-Campos A, Spong CY, Chandraharan E (2015) FIGO consensus guidelines on Intrapartum fetal monitoring. Int J Gynecol Obstet 131(1):13–24
Georgoulas G, Stylios D, Groumpos P (2006) Predicting the risk of metabolic acidosis for newborns based on fetal heart rate signal classification using support vector machines. IEEE Trans Biomed Eng 53:875–884
Ghodsi A (2006). Dimensionality reduction a short tutorial Department of Statistics and Actuarial Science, University of Waterloo.
Giussani DA (2016) The fetal brain sparing response to hypoxia: physiological mechanisms. J Physiol 594:1215–1230
Gogolewski K, Sykulski M, Chung NC, Gambin A (2019) Truncated robust principal component analysis and noise reduction for single cell RNA sequencing data. J Comput Biol. https://doi.org/10.1089/cmb.2018.0255
Guijarro-Berdinas B, Alonso-Betanzos A, Fontella-Romero O (2002) Intelligent analysis and pattern recognition in cardiotocographic signals using a tightly coupled hybrid system. Elsevier. Artificial Intelligence 136(1):1–27
Huang M-L, Hsu Y-Y (2012) Fetal distress prediction using discriminant analysis, decision tree, and artificial neural network. J Biomed Sci Eng 05:526–533
Macones GA et al (2008) The 2008 National Institute of Child Health and Human Development workshop report on electronic fetal monitoring: update on definitions, interpretation, and research guidelines. J Am College Obstet Gynecol 112:661–666
Maeda K (2014) Fetal hypoxia. J Health Med Informat. https://doi.org/10.1891/9780826172310.0015
Maeda K, Noguchi Y, Utsu M, Nagassawa K (2015) Algorithms for computerized fetal heart rate diagnosis with direct reporting. Algorithms 8(1):395–406
Murotsuki J, Bocking AD, Gagnon R (1997) Fetal heart rate patterns in growth restricted fetal sheep induced by chronic fetal placental embolization. Am J Obstet Gynecol 176(2):282–290
Ocak H (2013) A medical decision support system based on support vector machines and the genetic algorithm for the evaluation of fetal well-being. J Med Syst. https://doi.org/10.1007/s10916-012-9913-4
Ozyilmaz L, Yildirim T (2004) ROC analysis for fetal hypoxia problem by artificial neural networks. Artificial intelligence and soft computing—ICAISC 2004, volume 3070, lecture notes in artificial intelligence. Springer, Berlin, pp 1026–1030
Peng H, Long F, Ding C (2005) Feature selection based on mutual information: criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans Pattern Anal Mach Intell 27(8):1226–1238
Petrozziello A, Redman CWG, Papageorghiou AT, Jordanov I, Georgieva A (2019) Multimodal convolutional neural networks to detect fetal compromise during labor and delivery. IEEE Access 7(1):112026–112036
Preti M, Chandraharan E (2018) Importance of fetal heart rate cycling during the interpretation of the cardiotocograph (CTG). International Journal of Gynecology and Reproductive Sciences 1:11–12
Santo S, Ayres-de-Campos D, Santos C, Schnettler W, Ugwumadu A, Garca LMD (2017) Agreement and accuracy using the FIGO, ACOG and NICE cardiotocography interpretation guidelines. Acta Obstet Gynecol Scand 96(2):166–175
UCI Irvine Data Repository (n.d.) http://archive.ics.uci.edu/ml/datasets/Cardiotocography. Accessed 05/02/2019
Yilmaz E, Kilikçier C (2013) Determination of fetal state from Cardiotocogram using LSSVM with particle swarm optimization and binary decision tree. J Comput Math Methods Med 2013:1–8
Yılmaz E, Kılıkçıer Ç (2013) Determination of fetal state from Cardiotocogram using LS-SVM with particle swarm optimization and binary decision tree. Comput Math Methods Med 2013:1–8
Zhang Z, Castelló A (2017) Principal components analysis in clinical studies. Ann Transl Med 5(17):351–357
Zhu M, Xia J, Yan M et al (2015) Dimensionality reduction in complex medical data: improved self-adaptive niche genetic algorithm. Comput Math Methods Med 2015:1–12
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Das, S., Mukherjee, H., Obaidullah, S.M. et al. Ensemble based technique for the assessment of fetal health using cardiotocograph – a case study with standard feature reduction techniques. Multimed Tools Appl 79, 35147–35168 (2020). https://doi.org/10.1007/s11042-020-08853-2
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-020-08853-2