Cardiotocography (CTG) is a monitoring technique that provides vital information about fetal status during the antepartum and intrapartum periods. Manual interpretation of CTG often experiences high inter-observer variability and can lead to misdiagnosis. This study analyzes and compares various machine learning techniques in fetal heart rate classification for early detection of fetal complications. A comparative approach was employed by evaluating five machine learning algorithms: Artificial Neural Network (ANN), Support Vector Machine (SVM), Extreme Learning Machine (ELM), Radial Basis Function Network (RBFN), and Random Forest (RF). The dataset consisted of 2126 instances with 21 features obtained from the SisPorto 2.0 system, reduced to 1831 samples after excluding suspicious cases. The results demonstrated that ANN provided the best performance with a sensitivity of 99.73%, specificity of 97.94%, and overall accuracy of 97.87%. The study also identified that Combined Spinal-Epidural (CSE), bupivacaine dosage, and duration of the first stage of labor were important predictors of fetal heart rate changes. Feature importance analysis revealed that abnormal short-term variability (importance: 0.187) and abnormal long-term variability (importance: 0.156) were the most informative features for classification. These findings indicate that the machine learning approach can improve diagnostic accuracy and reduce variability in interpretation in fetal monitoring, thereby contributing to improved maternal and neonatal safety.
Research Article | Open Access | Download Full Text
Volume 5 | Issue 2 | Year 2026 | Article Id: DST-V5I2P101 DOI: https://doi.org/10.59232/DST-V5I2P101
Application of Machine Learning in Fetal Heart Rate Classification: Comparative Analysis for Early Detection of Fetal Complications
Emirul Bahar, Sri Hayuningsih, Erma Triawati Christina, Sri Hayuningsih, Dela Agustin, Auva Dita Nabila
| Received | Revised | Accepted | Published |
|---|---|---|---|
| 18 Jan 2026 | 17 Feb 2026 | 20 Mar 2026 | 30 Apr 2026 |
Citation
Emirul Bahar, Sri Hayuningsih, Erma Triawati Christina, Sri Hayuningsih, Dela Agustin, Auva Dita Nabila. “Application of Machine Learning in Fetal Heart Rate Classification: Comparative Analysis for Early Detection of Fetal Complications.” DS Journal of Digital Science and Technology, vol. 5, no. 2, pp. 1-14, 2026.
Abstract
Keywords
Artificial Neural Network, Cardiotocography, Classification, Early Detection, Fetal Complications, Fetal Heart Rate, Machine Learning.
References
[1] Ana Pinas, and Edwin Chandraharan, “Continuous Cardiotocography During Labour: Analysis, Classification and Management,” Best Practice and Research Clinical Obstetrics and Gynaecology, vol. 30, pp. 33-47, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Diogo Ayres-de-Campos, Catherine Y. Spong, and Edwin Chandraharan, “FIGO Consensus Guidelines on Intrapartum Fetal Monitoring: Cardiotocography,” International Journal of Gynecology and Obstetrics, vol. 131, no. 1, pp. 13-24, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Ingemar Ingemarsson, “Gender Aspects of Preterm Birth,” BJOG: An International Journal of Obstetrics and Gynaecology, vol. 110, pp. 34-38, 2003.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Anna-Karin Sundström, David Rosén, and K.G. Rosén, “Fetal Surveillance,” Gothenburg: Neoventa Medical AB, 2000.
[Google Scholar]
[5] Molly J. Stout, and Alison G. Cahill, “Electronic Fetal Monitoring: Past, Present, and Future,” Clinics in Perinatology, vol. 38, no. 1, pp. 127-142, 2011.
[CrossRef] [Google Scholar] [Publisher Link]
[6] E.S. Draper et al., “A Confidential Enquiry into Cases of Neonatal Encephalopathy,” Archives of Disease in Childhood-Fetal and Neonatal Edition, vol. 87, no. 3, pp. F176-F180, 2002.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Laura M. Glaser, Farah A. Alvi, and Magdy P. Milad, “Trends in Malpractice Claims for Obstetric and Gynecologic Procedures, 2005 Through 2014,” American Journal of Obstetrics and Gynecology, vol. 217, no. 3, pp. 340.e1-340.e6, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Zafer Cömert, and Adnan Fatih Kocamaz, “Evaluation of Fetal Distress Diagnosis During Delivery Stages based on Linear and Nonlinear Features of Fetal Heart Rate for Neural Network Community,” International Journal of Computer Applications, vol. 156, no. 4, pp. 26-31, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Mei-Ling Huang, and Yung-Yan Hsu, “Fetal Distress Prediction using Discriminant Analysis, Decision Tree, and Artificial Neural Network,” Journal of Biomedical Science and Engineering, vol. 5, no. 9, pp. 526-533, 2012.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Ersen Yılmaz, and Çağlar Kılıkçıer, “Determination of Fetal State from Cardiotocogram using LS-SVM with Particle Swarm Optimization and Binary Decision Tree,” Computational and Mathematical Methods in Medicine, vol. 2013, no. 1, pp. 1-8, 2013.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Radhika R. Halde, “Application of Machine Learning Algorithms for Betterment in Education System,” 2016 International Conference on Automatic Control and Dynamic Optimization Techniques (ICACDOT), Pune, India, pp. 1110-1114, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Sahana Das et al., “A Machine Learning Pipeline to Classify Fetal Heart Rate Deceleration with Optimal Feature Set,” Scientific Reports, vol. 13, no. 1, pp. 1-20, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Efrain Riveros-Perez, Javier Jose Polania-Gutierrez, and Bibiana Avella-Molano, “Fetal Heart Rate Changes and Labor Neuraxial Analgesia: A Machine Learning Approach,” BMC Pregnancy and Childbirth, vol. 23, no. 1, pp. 1-7, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Z. Comert, and A.F. Kocamaz, “Comparison of Machine Learning Techniques for Fetal Heart Rate Classification,” Acta Physica Polonica A, vol. 132, no. 3, pp. 451-454, 2017.
[CrossRef] [Google Scholar]
[15] Hasan Ocak, “A Medical Decision Support System based on Support Vector Machines and the Genetic Algorithm for the Evaluation of Fetal Well-Being,” Journal of Medical Systems, vol. 37, no. 2, 2013.
[CrossRef] [Google Scholar] [Publisher Link]
[16] 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, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Jiří Spilka et al., “Sparse Support Vector Machine for Intrapartum Fetal Heart Rate Classification,” IEEE Journal of Biomedical and Health Informatics, vol. 21, no. 3, pp. 664-671, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Guang-Bin Huang, Qin-Yu Zhu, and Chee-Kheong Siew, “Extreme Learning Machine: Theory and Applications,” Neurocomputing, vol. 70, no. 1-3, pp. 489-501, 2006.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Diogo Ayres-de-campos et al., “SisPorto 2.0: A Program for Automated Analysis of Cardiotocograms,” Journal of Maternal-Fetal Medicine, vol. 9, no. 5, pp. 311-318, 2000.
[Google Scholar] [Publisher Link]
[20] Zafer Cömert, and Adnan Fatih Kocamaz, “Fetal Hypoxia Detection based on Deep Convolutional Neural Network with Transfer Learning Approach,” Software Engineering and Algorithms in Intelligent Systems: Proceedings of 7th Computer Science On-line Conference, Springer, Cham, vol. 1, pp. 239-248, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[21] Jiří Spilka et al., “Automatic Evaluation of FHR Recordings from CTU-UHB CTG Database,” Information Technology in Bio- and Medical Informatics: 4th International Conference, ITBAM 2013, Prague, Czech Republic, vol. 8060, pp. 47-61, 2013.
[CrossRef] [Google Scholar] [Publisher Link]
[22] K. Warwick, and R. Craddock, “An Introduction to Radial basis Functions for System Identification. A Comparison with Other Neural Network Methods,” Proceedings of 35th IEEE Conference on Decision and Control, Kobe, Japan, vol. 1, pp. 464-469, 1996.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Peterek Tomáš et al., “Classification of Cardiotocography Records by Random Forest,” 2013 36th International Conference on Telecommunications and Signal Processing (TSP), Rome, Italy, pp. 620-923, 2013.
[CrossRef] [Google Scholar] [Publisher Link]
[24] J. Nicolet et al., “Maternal Factors Implicated in Fetal Bradycardia after Combined Spinal Epidural for Labour Pain,” European Journal of Anaesthesiology, vol. 25, no. 9, pp. 721-725, 2008.
[CrossRef] [Google Scholar] [Publisher Link]