Abstract
In non-stress tests (NST) of antenatal fetal monitoring, the computerized cardiotocography (CTG) interpretation plays an important role. The digital CTG data are widely available, however, the number of abnormal cases is quite lower than that of the suspicious or normal cases. This phenomenon is referred to as imbalanced multi-classification, which has brought great challenge for machine learning to assess fetuses’ health status. Therefore, in this paper we aim to establish an intelligent evaluation model using imbalanced CTG data for monitoring fetuses’ growth. After data exploration, a weighted random forest (WRF) model was established by adjusting category weights to fulfill cost-sensitive learning. The efficiency of the proposed model was tested on the antenatal CTG dataset from the UCI repository. The WRF model achieved an average area under the receiver operating characteristic curve (ROC) of 0.99. Meanwhile, the average F1 score for the WRF (97.56%) exceeded that of the existing state-of-the-art models. The experimental results showed that the proposed model was promising for intelligent evaluating antenatal fetal health status using seriously imbalanced CTG data.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Haran, S., Everett, T.R.: Antenatal fetal wellbeing. Obstet. Gynaecol. Reprod. Med. 27(2), 44–49 (2017)
Grivell, R.M., Alfirevic, Z., Gyte, G.M.L., et al.: Antenatal cardiotocography for fetal assessment. Cochrane Libr. (2015)
Gagnon, R., Campbell, M.K., Hunse, C.A.: comparison between visual and computer analysis of antepartum fetal heart rate tracings. Am. J. Obstet. Gynecol. 168(3 Pt 1), 842 (1993)
Xie, X., Yan, W.: Obstetrics and Gynecology, 8 edn, pp. 118–120. People’s Medical Publishing House, Beijing (2013)
Ocak, H., Ertunc, H.M.: Prediction of fetal state from the cardiotocogram recordings using adaptive neuro-fuzzy inference systems. Neural Comput. Appl. 23(6), 1583–1589 (2013)
Ocak, H.: A medical decision support system based on support vector machines and the genetic algorithm for the evaluation of fetal well-being. J. Med. Syst. 37(2), 9913 (2013)
Yılmaz, E.: Fetal state assessment from cardiotocogram data using artificial neural networks. J. Med. Biol. Eng. 36(6), 820–832 (2016)
Huang, M.L., Hsu, Y.Y.: Fetal distress prediction using discriminant analysis, decision tree, and artificial neural network. J. Biomed. Sci. Eng. 05(9), 526 (2012)
Sundar, C.M., Chitradevi, M.C., Geetharamani, G.: Classification of cardiotocogram data using neural network based machine learning technique. Int. J. Comput. Appl. 47(14), 19–25 (2013)
Karabulut, E.M., Ibrikci, T.: Analysis of cardiotocogram data for fetal distress determination by decision tree based adaptive boosting approach. J. Comput. Commun. 02(9), 32–37 (2014)
Arif, M.: Classification of cardiotocograms using random forest classifier and selection of important features from cardiotocogram signal. Biomater. Biomech. Bioeng. 2(3), 173–183 (2015)
Yilmaz, E., Kilikçier, Ç.: Determination of fetal state from cardiotocogram using LS-SVM with particle swarm optimization and binary decision tree. Comput. Math. Methods Med. 2013(2), 487179 (2013)
State Statistical Bureau. Statistical Yearbook of China. China Statistics Press, Beijing (2017)
Ravindran, S., Jambek, A.B., Muthusamy, H., et al.: A novel clinical decision support system using improved adaptive genetic algorithm for the assessment of fetal well-being. Comput. Math. Methods Med. 2015, 11 (2015)
Asuncion, A., Newman, D.: UCI machine learning repository (2007)
Ayresde, C.D., Bernardes, J., Garrido, A., et al.: SisPorto 2.0: a program for automated analysis of cardiotocograms. J. Matern.-Fetal Med. 9(5), 311–318 (2000)
Alfirevic, Z., Devane, D., Gyte, G.M.: Continuous cardiotocography (CTG) as a form of electronic fetal monitoring (EFM) for fetal assessment during labour. Cochrane Libr. 19(3), CD006066 (2006)
Cheng, Z., Song, S.: Fetal electronic monitoring, 81–92 (2001)
Lyons, E.R., Bylsma-Howell, M., Shamsi, S., et al.: A scoring system for nonstressed antepartum fetal heart rate monitoring. Am. J. Obstet. Gynecol. 133(3), 242–246 (1979)
Tian, C.: NST score and modified fischer scoring method to evaluate the correlation between fetal test results and newborn birth. CJ 16(22), 28–29 (2009)
Society of obstetricians and gynaecologists of Canada. SOGC clinical practice guidelines. Guidelines for vaginal birth after previous caesarean birth. Number 155 (Replaces guideline Number 147), February 2005. Int. J. Gynaecol. Obstet. 89(3), 319 (2005)
Santo, S., Ayres-de-Campos, D., Costa-Santos, C., et al.: Agreement and accuracy using the FIGO, ACOG and NICE cardiotocography interpretation guidelines. Acta Obstet. Gynecol. Scand. 96(2), 166–175 (2017)
Ayres-de-Campos, D., Spong, C.Y., Chandraharan, E.: FIGO consensus guidelines on intrapartum fetal monitoring: cardiotocography. Int. J. Gynecol. Obstet. 131(1), 13–24 (2015)
Chinese society of perinatal medicine. expert consensus on the application of electronic fetal heart rate monitoring. Chin. J. Perinat. Med. 2015(7), 486–490 (2015)
Xie, X., Kong, B., Duan, T.: Gynecology and Obstetrics, 9th Edn, pp. 54–56. People’s Health Publishing House, Beijing (2018)
Zhang, H.: Graphic analysis and management of 368 cases of abnormal non-stress test in fetal monitoring. Gen. Nurs. 14(36), 3837–3838 (2016)
Acknowledgement
This work is supported by The Medical Scientific Research Foundation of Guangdong Province under Grant No. A2019428, and the Natural Science Foundation of Guangdong Province under Grant No. 2015A030310312.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Chen, Jy. et al. (2019). Imbalanced Cardiotocography Multi-classification for Antenatal Fetal Monitoring Using Weighted Random Forest. In: Chen, H., Zeng, D., Yan, X., Xing, C. (eds) Smart Health. ICSH 2019. Lecture Notes in Computer Science(), vol 11924. Springer, Cham. https://doi.org/10.1007/978-3-030-34482-5_7
Download citation
DOI: https://doi.org/10.1007/978-3-030-34482-5_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-34481-8
Online ISBN: 978-3-030-34482-5
eBook Packages: Computer ScienceComputer Science (R0)