A Study of Artificial Neural Network Training Algorithms for Classification of Cardiotocography Signals

Cardiotocography (CTG) that contains fetal heart rate (FHR) and uterine contraction (UC) signals is a monitoring technique. During the last decades, FHR signals have been classified as normal, suspicious, and pathological using machine learning techniques. As a classifier, artificial neural network (ANN) is notable due to its powerful capabilities. For this reason, behaviors and performances of neural network training algorithms were investigated and compared on classification task of the CTG traces in this study. Training algorithms of neural network were categorized in five group as Gradient Descent, Resilient Backpropagation, Conjugate Gradient, Quasi-Newton, and Levenberg-Marquardt. Two different experimental setups were performed during the training and test stages to achieve more generalized results. Furthermore, several evaluation parameters, such as accuracy (ACC), sensitivity (Se), specificity (Sp), and geometric mean (GM), were taken into account during performance comparison of the algorithms. An open access CTG dataset containing 2126 instances with 21 features and located under UCI Machine Learning Repository was used in this study. According to results of this study, all training algorithms produced rather satisfactory results. In addition, the best classification performances were obtained with Levenberg-Marquardt backpropagation (LM) and Resilient Backpropagation (RP) algorithms. The GM values of RP and LM were obtained as 89.69% and 86.14%, respectively. Consequently, this study confirms that ANN is a useful machine learning tool to classify FHR recordings.

[1]  Zafer Cömert,et al.  Cardiotocography signals with artificial neural network and extreme learning machine , 2016, 2016 24th Signal Processing and Communication Application Conference (SIU).

[2]  Martin A. Riedmiller,et al.  A direct adaptive method for faster backpropagation learning: the RPROP algorithm , 1993, IEEE International Conference on Neural Networks.

[3]  Hasan Ocak,et al.  A Medical Decision Support System Based on Support Vector Machines and the Genetic Algorithm for the Evaluation of Fetal Well-Being , 2013, Journal of Medical Systems.

[4]  Ersen Yilmaz,et al.  Fetal State Assessment from Cardiotocogram Data Using Artificial Neural Networks , 2016 .

[5]  M. J. D. Powell,et al.  Restart procedures for the conjugate gradient method , 1977, Math. Program..

[6]  Petr Gajdos,et al.  Classification of cardiotocography records by random forest , 2013, 2013 36th International Conference on Telecommunications and Signal Processing (TSP).

[7]  Jukka Saarinen,et al.  Feature selection method using neural network , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[8]  John E. Dennis,et al.  Numerical methods for unconstrained optimization and nonlinear equations , 1983, Prentice Hall series in computational mathematics.

[9]  Diogo Ayres-de-Campos,et al.  Computer analysis of foetal monitoring signals. , 2016, Best practice & research. Clinical obstetrics & gynaecology.

[10]  Martin Fodslette Meiller.  A Scaled Conjugate Gradient Algorithm for Fast Supervised Learning , 1993 .

[11]  Ashraf M. Abdelbar,et al.  Levenberg-Marquardt and Conjugate Gradient methods applied to a high-order neural network , 2013, The 2013 International Joint Conference on Neural Networks (IJCNN).

[12]  Z. Alfirevic,et al.  Antenatal cardiotocography for fetal assessment. , 2012, The Cochrane database of systematic reviews.

[13]  Roberto Battiti,et al.  First- and Second-Order Methods for Learning: Between Steepest Descent and Newton's Method , 1992, Neural Computation.

[14]  Yang Zhang,et al.  Fetal state assessment based on cardiotocography parameters using PCA and AdaBoost , 2017, 2017 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI).

[15]  Ahmad Taher Azar,et al.  Fast neural network learning algorithms for medical applications , 2012, Neural Computing and Applications.

[16]  Mei-Ling Huang,et al.  Fetal distress prediction using discriminant analysis, decision tree, and artificial neural network , 2012 .

[17]  D. Ayres-de-Campos,et al.  FIGO consensus guidelines on intrapartum fetal monitoring: Cardiotocography , 2015, International journal of gynaecology and obstetrics: the official organ of the International Federation of Gynaecology and Obstetrics.

[18]  Jon Rigelsford.  Handbook of Neural Network Signal Processing , 2003 .

[19]  Janusz Wrobel,et al.  Analysis of extracted cardiotocographic signal features to improve automated prediction of fetal outcome , 2010 .

[20]  D. Ayres-de- Campos,et al.  SisPorto 2.0: a program for automated analysis of cardiotocograms. , 2000, The Journal of maternal-fetal medicine.

[21]  Zafer Cömert,et al.  Evaluation of Fetal Distress Diagnosis during Delivery Stages based on Linear and Nonlinear Features of Fetal Heart Rate for Neural Network Community , 2016 .

[22]  W. Piyamongkol,et al.  Accuracy of fetal heart‐rate variability interpretation by obstetricians using the criteria of the National Institute of Child Health and Human Development compared with computer‐aided interpretation , 2005, The journal of obstetrics and gynaecology research.

[23]  Mark Beale,et al.  Neural Network Toolbox™ User's Guide , 2015 .

[24]  I A Basheer,et al.  Artificial neural networks: fundamentals, computing, design, and application. , 2000, Journal of microbiological methods.

[25]  E. Chandraharan,et al.  Continuous cardiotocography during labour: Analysis, classification and management. , 2016, Best practice & research. Clinical obstetrics & gynaecology.

[26]  Mohamed El Bachir Menai,et al.  Influence of Feature Selection on Naïve Bayes Classifier for Recognizing Patterns in Cardiotocograms , 2013 .

[27]  Barry J. Wythoff,et al.  Backpropagation neural networks , 1993 .

[28]  Yunming Ye,et al.  Classification of Cardiotocogram Data using Neural Network based Machine Learning Technique , 2012 .

[29]  L. Lhotska,et al.  Evaluation of feature subsets for classification of cardiotocographic recordings , 2008, 2008 Computers in Cardiology.

[30]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[31]  Mohammad Bagher Menhaj,et al.  Training feedforward networks with the Marquardt algorithm , 1994, IEEE Trans. Neural Networks.

[32]  Turgay Ibrikci,et al.  Analysis of Cardiotocogram Data for Fetal Distress Determination by Decision Tree Based Adaptive Boosting Approach , 2014 .

[33]  Abdulhamit Subasi,et al.  Classification of the cardiotocogram data for anticipation of fetal risks using machine learning techniques , 2015, Appl. Soft Comput..

[34]  M. Hariharan,et al.  A Novel Clinical Decision Support System Using Improved Adaptive Genetic Algorithm for the Assessment of Fetal Well-Being , 2015, Comput. Math. Methods Medicine.

[35]  M. K. Soni,et al.  Artificial Neural Network-Based Peak Load Forecasting Using Conjugate Gradient Methods , 2002, IEEE Power Engineering Review.

[36]  Stefan Fritsch,et al.  neuralnet: Training of Neural Networks , 2010, R J..

[37]  Janusz Jezewski,et al.  Computerized analysis of fetal heart rate signals as the predictor of neonatal acidemia , 2012, Expert Syst. Appl..

[38]  Maria Romano,et al.  An algorithm for the recovery of fetal heart rate series from CTG data , 2007, Comput. Biol. Medicine.

[39]  Zafer Cömert,et al.  Cardiotocography analysis based on segmentation-based fractal texture decomposition and extreme learning machine , 2017, 2017 25th Signal Processing and Communications Applications Conference (SIU).

[40]  Qeethara Al-Shayea.  Artificial Neural Networks in Medical Diagnosis , 2024, International Journal of Research Publication and Reviews.

[41]  Zafer Cömert,et al.  Comparison of Machine Learning Techniques for Fetal Heart Rate Classification , 2017 .