Cardiotocography Data Analysis to Predict Fetal Health Risks with Tree-Based Ensemble Learning

Full Text (PDF, 480KB), PP.30-40

Views: 0 Downloads: 0

Author(s)

Pankaj Bhowmik 1,* Pulak Chandra Bhowmik 2 U. A. Md. Ehsan Ali 3 Md. Sohrawordi 3

1. Dept. of Computer Science & Engineering, Hajee Mohammad Danesh Science and Technology University, Bangladesh

2. Dept. of Computer Science & Engineering, Stamford University Bangladesh, Dhaka, Bangladesh

3. Dept. of Computer Science & Engineering, Hajee Mohammad Danesh Science and Technology University, Dinajpur-5200, Bangladesh

* Corresponding author.

DOI: https://doi.org/10.5815/ijitcs.2021.05.03

Received: 26 May 2021 / Revised: 13 Jul. 2021 / Accepted: 29 Jul. 2021 / Published: 8 Oct. 2021

Index Terms

Ensemble Learning, Stacking, Cardiotocography, Hyperparameter Tuning, Feature Selection, Cross Validation, Random Forest classifier

Abstract

A sizeable number of women face difficulties during pregnancy, which eventually can lead the fetus towards serious health problems. However, early detection of these risks can save both the invaluable life of infants and mothers. Cardiotocography (CTG) data provides sophisticated information by monitoring the heart rate signal of the fetus, is used to predict the potential risks of fetal wellbeing and for making clinical conclusions. This paper proposed to analyze the antepartum CTG data (available on UCI Machine Learning Repository) and develop an efficient tree-based ensemble learning (EL) classifier model to predict fetal health status. In this study, EL considers the Stacking approach, and a concise overview of this approach is discussed and developed accordingly. The study also endeavors to apply distinct machine learning algorithmic techniques on the CTG dataset and determine their performances. The Stacking EL technique, in this paper, involves four tree-based machine learning algorithms, namely, Random Forest classifier, Decision Tree classifier, Extra Trees classifier, and Deep Forest classifier as base learners. The CTG dataset contains 21 features, but only 10 most important features are selected from the dataset with the Chi-square method for this experiment, and then the features are normalized with Min-Max scaling. Following that, Grid Search is applied for tuning the hyperparameters of the base algorithms. Subsequently, 10-folds cross validation is performed to select the meta learner of the EL classifier model. However, a comparative model assessment is made between the individual base learning algorithms and the EL classifier model; and the finding depicts EL classifiers’ superiority in fetal health risks prediction with securing the accuracy of about 96.05%. Eventually, this study concludes that the Stacking EL approach can be a substantial paradigm in machine learning studies to improve models’ accuracy and reduce the error rate.

Cite This Paper

Pankaj Bhowmik, Pulak Chandra Bhowmik, U. A. Md. Ehsan Ali, Md. Sohrawordi, "Cardiotocography Data Analysis to Predict Fetal Health Risks with Tree-Based Ensemble Learning", International Journal of Information Technology and Computer Science(IJITCS), Vol.13, No.5, pp.30-40, 2021. DOI:10.5815/ijitcs.2021.05.03

Reference

[1] Dua, D. and Graff, C., “UCI machine learning repository,” [Online]. Available: archive.ics.uci.edu/ml/datasets/Cardiotocography
[2] Ayres de Campos, Diogo, et al. “SisPorto 2.0: a program for automated analysis of cardiotocograms”, Journal of Maternal-Fetal Medicine, vol. 9, no.5, pp. 311-318, Sep-Oct 2000.
[3] Md Zannatul Arif, Rahate Ahmed, Umma Habiba Sadia, Mst Shanta Islam Tultul and Rocky Chakma, "Decision Tree Method Using for Fetal State Classification from Cardiotography Data," Journal of Advanced Engineering and Computation, vol. 4, no. 1, pp. 64-73, March 2020.
[4] Abdulhamit Subasi, Bayader Kadasa and Emir Kremic, "Classification of the Cardiotocogram Data for Anticipation of Fetal Risks using Bagging Ensemble Classifier," Procedia Computer Science, vol. 168, pp. 34-39, 2020.
[5] Sahana Das, Himadri Mukherjee, Sk. Md. Obaidullah, Kaushik Roy and Chanchal Kumar Saha, "Ensemble based technique for
the assessment of fetal health using cardiotocograph – a case study with standard feature reduction techniques," Multimedia Tools and Applications, vol. 79, issue 47-48, pp. 35147 - 35168, April 2020.
[6] Jia-ying Chen, Xiao-cong Liu, Hang Wei, Qin-qun Chen, Jia-ming Hong, Qiong-na Li and Zhi-feng Hao, "Imbalanced Cardiotocography Multi-classification for Antenatal Fetal Monitoring Using Weighted Random Forest," International Conference, ICSH 2019, Shenzhen, China, pp. 75-85, July 2019, Springer, Cham.
[7] Hakan Sahin and Abdulhamit Subasi, "Classification of the cardiotocogram data for anticipation of fetal risks using machine learning techniques," Applied Soft Computing, vol. 33, pp. 231-238, August 2015.
[8] Mohammad Saber Iraji, "Prediction of fetal state from the cardiotocogram recordings using neural network models," Artificial Intelligence in Medicine, vol. 96, pp. 33-44, May 2019.
[9] Septian Eko Prasetyo, Pulung Hendro Prastyo and Shindy Arti, "A Cardiotocographic Classification using Feature Selection: A Comparative Study," Journal of Information Technology and Computer Engineering (JITCE), vol. 5, no. 01, pp. 25-32, March 2021.
[10] Sumedh Anand Sontakke, Jay Lohokare, Reshul Dani and Pranav Shivagaje, "Classification of Cardiotocography Signals using Machine Learning," 2018 Intelligent Systems Conference (IntelliSys), pp. 439-450, Springer, Cham.
[11] E. Kannan, S. Ravikumar, A. Anitha, Sathish A. P. Kumar and M. Vijayasarathy, "Analyzing uncertainty in cardiotocogram data for the prediction of fetal risks based on machine learning techniques using rough set," Journal of Ambient Intelligence and Humanized Computing, January 2021.
[12] Susan Yuhou Xia, “Using a Stacking Model Ensemble Approach to Predict Rare Events,” Conference Talks, SciPy 2019, 18th annual Scientific Computing with Python Conference, in Austin, Texas, USA. [Online]. Available: youtube.com/watch?v=6oD5K0x1k7c&t=551s
[13] M. M. Imran Molla, Julakha Jahan Jui, Bifta Sama Bari, Mamunur Rashid and Md Jahid Hasan, "Cardiotocogram Data Classification Using Random Forest Based Machine Learning Algorithm," Proceedings of the 11th National Technical Seminar on Unmanned System Technology 2019, Lecture Notes in Electrical Engineering, vol 666. Springer, Singapore.
[14] Syifa Fauziyah Nurul Islam and Intan Nurma Yulita, "Predicting Fetal Condition from Cardiotocography Results Using the Random Forest Method," 7th Mathematics, Science, and Computer Science Education International Seminar, MSCEIS 2019, Bandung, West Java, Indonesia.
[15] Yandi Chen, Ao Guo, Qinqun Chen, Bin Quan, Guiqing Liu, Li Li, Jiaming Hong, Hang Wei and Zhifeng Hao, "Intelligent classification of antepartum cardiotocography model based on deep forest," Biomedical Signal Processing and Control, vol. 67, Article 102555, May 2021.
[16] Satish Chandra Reddy Nandipati, "Classification and Feature Selection Approaches for Cardiotocography by Machine Learning Techniques", Journal of Telecommunication, Electronic and Computer Engineering, vol. 12, no. 1, pp. 7-14, January - March 2020.
[17] Zhi-Hua Zhou and Ji Feng, "Deep Forest," National Science Review, vol. 6, no. 1, pp. 74-86, Jan. 2019.
[18] Sundar.C, M. Chitradevi and G. Geetharamani, "Classification of Cardiotocogram Data using Neural Network based Machine Learning Technique", International Journal of Computer Applications, vol. 47, no. 14, pp.19-25, June 2012.
[19] K. Agrawal and H. Mohan, "Cardiotocography Analysis for Fetal State Classification Using Machine Learning Algorithms," 2019 International Conference on Computer Communication and Informatics (ICCCI), 2019, pp. 1-6, doi: 10.1109/ICCCI.2019.8822218
[20] M. Ramla, S. Sangeetha and S. Nickolas, "Fetal Health State Monitoring Using Decision Tree Classifier from Cardiotocography Measurements," 2018 Second International Conference on Intelligent Computing and Control Systems (ICICCS), 2018, pp. 1799-1803, doi: 10.1109/ICCONS.2018.8663047
[21] S. A. A. Shah, W. Aziz, M. Arif and M. S. A. Nadeem, "Decision Trees Based Classification of Cardiotocograms Using Bagging Approach," 2015 13th International Conference on Frontiers of Information Technology (FIT), 2015, pp. 12-17, doi: 10.1109/FIT.2015.14
[22] P. Bhowmik, M. Sohrawordi, U. A. M. Ehsan Ali, M. N. Hasan and P. K. Roy, "Analysis of Social Media Data to Classify and Detect Frequent Issues Using Machine Learning Approach," 2020 2nd International Conference on Advanced Information and Communication Technology (ICAICT), 2020, pp. 394-399, doi: 10.1109/ICAICT51780.2020.9333452
[23] Xianping Du, Hongyi Xu and Feng Zhu, "Understanding the Effect of Hyperparameter Optimization on Machine Learning Models for Structure Design Problems," Computer-Aided Design, vol. 135, Article 103013, 2021, doi: 10.1016/j.cad.2021.103013
[24] Abdullah Al Imran, Ananya Rahman, Humayoun Kabir, Shamsur Rahim, "The Impact of Feature Selection Techniques on the Performance of Predicting Parkinson’s Disease", International Journal of Information Technology and Computer Science, Vol.10, No.11, pp.14-29, 2018.
[25] Sahana Das, Kaushik Roy, Chanchal K. Saha, "Establishment of Automated Technique of FHR Baseline and Variability Detection Using CTG: Statistical Comparison with Expert’s Analysis", International Journal of Information Engineering and Electronic Business, Vol.11, No.1, pp. 27-35, 2019.
[26] Kemal Akyol, Baha Şen, "Diabetes Mellitus Data Classification by Cascading of Feature Selection Methods and Ensemble Learning Algorithms", International Journal of Modern Education and Computer Science, Vol.10, No.6, pp. 10-16, 2018.
[27] Rafael M.O. Cruz, Robert Sabourin, George D.C. Cavalcanti, Tsang Ing Ren, "META-DES: A dynamic ensemble selection framework using meta-learning", Pattern Recognition, vol. 48, no. 5, pp. 1925-1935, May 2015, DOI: 10.1016/j.patcog.2014.12.003
[28] R. Afridi, Z. Iqbal, M. Khan, A. Ahmad, and R. Naseem, "Fetal Heart Rate Classification and Comparative Analysis Using Cardiotocography Data and Known Classifiers", International Journal of Grid and Distributed Computing (IJGDC), ISSN: 2005-4262 (Print); 2207-6379 (Online), NADIA, vol. 12, no. 1, pp. 31-42, Jun 2019.