Cardiotocography (CTG) records fetal heart rate (FHR) and uterine contractions (UC) simultaneously. Cardiotocography trace patterns help doctors to understand the state of the fetus. Even after the introduction of cardiotocograph, the capacity to predict is still inaccurate. This paper evaluates some commonly used classification methods using WEKA. Precision,Recall, F-Measrue and ROC curve have been used as the metric to evaluate the performance of classifiers. As opposed to some of the earlier research works that were unable to identify Suspicious and Pathologic patterns, the results obtained from the study in this paper could precisely identify pathologic and Suspicious cases. Best results were obtained from J48, Random Forest and Classification via Regression.
Divya Bhatnagar : is working as Professor in the department of Computer Science and Engineering in School of Engineering, Sir Padampat Singhania University, Udaipur, India. She holds 18 years of teaching and research experience. Her specialization areas include data mining and Neural Networks.
Piyush Maheshwari : has completed B. Tech. and M. Tech. in Computer Science and Engineering from Sir Padampat Singhania University, Udaipur, India. Udaipur, Rajasthan. His area of interest is data mining.
Cardiotocography, CTG, Fetal Heart Rate, Uterine Contractions, Data Mining, Classification, Data Analysis
Earlier, the research works analyzed the same data and observed that maximum accuracy is achieved from ANN as 92.42%. The results obtained from classification of CTG in this paper indicates that the most promising results are received from decision tree based algorithm (J48) with 0.0408 as MAE, 0.8716 as kappa statistics and 94.33% as accuracy with the highest value for precision metric. Random forest and Classification via Regression were close to J48. Area under the ROC curve indicated the maximum accuracy of the three classifiers J48, Random Forest and Classification via Regression.
In future other data mining techniques can be applied for getting more accurate results especially applying on attribute selected data. Future works may also address hybrid models for improved classification accuracy.
[1] Shahad Nidhal, M. A. Mohd. Ali and Hind Najah. 2010. A novel cardiotocography fetal heart rate baseline estimation algorithm. Scientific Research and Essays Vol. 5(24), pp. 4002-4010
[2] Antonia Costa, Diogo Ayres-de-Campos, Fernanda Costa, Cristina Santos, Joao Bernardes. 2009. Prediction of neonatal acidemia by computer analysis of fetal heart rate and ST event signals. American Journal of Obstetrics and Gynecology
[3] Huang, M. and Hsu, Y. (2012) Fetal Distress Prediction Using Discriminant Analysis, Decision Tree, and ArtificialNeural Network. Journal of Biomedical Science & Engineering, 5, 526-533.
[4] Sunder, C., Chitradevi, M. and Geetharamani, G. 2012 Classification of Cardiotocogram Data Using Neural NetworkBased Machine Learning Technique. International Journal of Computer Applications, 47, 19-25.
[5] Sunder, C., Chitradevi, M. and Geetharamani, G. 2012 An Analysis on the Performanace of K-Means Clustering Algorithm for Cardiotocogram Data Clustering. International Journal on Computational Sciences & Applications (IJCSA), 2(5), 11-20.
[6] Sundar, C., Chitradevi, M. and Geetharamani, G. 2013 An Overview of Research Challenges for Classification of Cardiotocogram Data. Journal of Computer Science, 9, 198-206
[7] Yilmaz, E. and Kilikçier, Ç. 2013 Determination of Fetal State from Cardiotocogram Using LS-SVM with ParticleSwarm Optimization and Binary Decision Tree. Computational and Mathematical Methods in Medicine, 2013.
[8] Newman, D.J., Heittech, S., Blake, C.L. and Merz, C.J. 1998. UCI Repository of Machine Learning Databases. University California Irvine, Department of Information and Computer Science.
[9] Kuncheva L. 2004 Combining Pattern Classifiers Methods and Algorithms. Wiley-Interscience, 360.
[10] Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P. and Witten, I.H. The WEKA Data Mining Software: AnUpdate. SIGKDD Explorations.
[11] Usama Fayyad, Gregory Piatetsky-Shapiro, Padhraic Smyth, and Ramasamy Uthurasamy, "Advances in Knowledge Discovery and Data Mining", AAAI Press/ The MIT Press, 1996.
[12] Julie M. David and Kannan Balakrishnan, “Significance of Classification Techniques in Prediction of Learning Disabilities”,
[13] Lichman, M. (2013). UCI Machine Learning Repository [http://archive.ics.uci.edu/ml]. Irvine, CA: University of California, School of Information and Computer Science.
[14] Kamel E., www.dremeilkamel.com.au /patient-information/obstetrics/cardiotocography-ctg.
[15] http://www.cs.waikato.ac.nz/ml/weka
