Deep Learning Approach for Fetal Health Prediction

Dr. S. Regina Lourdhu Suganthi; Mary Basilica

doi:10.32628/CSEIT241051041

Authors

Dr. S. Regina Lourdhu Suganthi Department of Computer Science, Mount Carmel College Autonomous, #58, Palace Road, Vasanth Nagar, Bengaluru, Karnataka, India Author
Mary Basilica Department of Computer Science, Mount Carmel College Autonomous, #58, Palace Road, Vasanth Nagar, Bengaluru, Karnataka, India Author

DOI:

https://doi.org/10.32628/CSEIT241051041

Keywords:

Fetal Health, CTG, Feature Selection, Genetic Algorithm, Particle Swarm Optimization, Multi-class Classification, Deep Learning, Convolution Neural Network, Artificial Neural Network

Abstract

Monitoring the foetus's health is crucial during pregnancy to avoid complications that may worsen the course of pregnancy and delivery. Cardiotocography (CTG) is a tool that provides complex information by monitoring the foetus's heart rate signal. Obstetricians visually interpret these signals to predict potential risks and draw clinical inferences. The interpretation, however, relies on the expertise of the obstetrician, leading to a significant false positive rate. Thus, the study uses deep learning techniques to effectively identify foetal health states as 'Normal', 'Suspect' and 'Pathological'. The dataset used is CTG data drawn from the Kaggle repository. The optimal subset of features is obtained by comparing traditional feature selection and meta-heuristic-based feature selection techniques. Deep learning algorithms, namely, Convolution Neural Networks, Artificial Neural Networks, and Radial Basis Function Networks, are applied to train multi-class classification models that predict foetal health status. The models are then evaluated using performance metrics.

Downloads

Download data is not yet available.

References

Y. Zhang and Z. Zhao (2017) Fetal state assessment based on cardiotocography parameter using PCA and AdaBoost. 10th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI). doi: 10.1109/CISP-BMEI.2017.8302314.

Z. Cömert, A.F. Kocamaz (2017) Comparison of Machine Learning Techniques for Fetal Heart Rate Classification. 3rd International Conference on Computational and Experimental Science and Engineering (ICCESEN).

Subasi, Abdulhamit & Kadasa, Bayader & Kremic, Emir (2020) Classification of the Cardiotocogram Data for Anticipation of Fetal Risks using Bagging Ensemble Classifier. Procedia Computer Science. https://doi.org/10.1016/j.procs.2020.02.248

M. Ramla, S. Sangeetha and S. Nickolas (2018 ) Fetal Health State Monitoring Using Decision Tree Classifier from Cardiotocography Measurements. Second International Conference on Intelligent Computing and Control Systems (ICICCS). doi: 10.1109/ICCONS.2018.8663047.

Hoodbhoy, Dr & Noman, Mohammad & Shafique, Ayesha & Nasim, Ali & Chowdhury, Devyani & Hasan, Babar (2019) Use of Machine Learning Algorithms for Prediction of Fetal Risk using Cardiotocographic Data. International Journal of Applied and Basic Medical Research. 2019. 10.4103/ijabmr.IJABMR_370_18.

Nabillah Rahmayanti, Humaira Pradani, Muhammad Pahlawan, and Retno Vinarti (2021) Comparison of machine learning algorithms to classify fetal health using cardiotocogram data. Sixth Information Systems International Conference (ISICO 2021). doi:10.1016/j.procs.2021.12.130

Bhowmik, Pankaj & Bhowmik, Pulak & Ali, U A Md Ehsan & Sohrawordi, Md. (2021) Cardiotocography Data Analysis to Predict Fetal Health Risks with Tree-Based Ensemble Learning. International Journal of Information Technology and Computer Science. 2021.13. 30-40. 10.5815/ijitcs.2021.05.03.

Eko Prasetyo, Septian & Prastyo, Hendro & Arti, Shindy (2021) A Cardiotocographic Classification using Feature Selection: A Comparative Study. JITCE (Journal of Information Technology and Computer Engineering). 2021. 5. 25-32. 10.25077/jitce.5.01.25-32.2021.

Das, Sahana & Mukherjee, Himadri & Sk, Obaidullah & Roy, Kaushik & Saha, Chanchal (2020) Ensemble-based technique for the assessment of fetal health using cardiotocograph – a case study with standard feature reduction techniques. Multimedia Tools and Applications. 2020. 79. 10.1007/s11042-020-08853-2.

V. Nagendra, H. Gude, D. Sampath, S. Corns and S. Long (2017) Evaluation of support vector machines and random forest classifiers in a real-time fetal monitoring system based on cardiotocography data. 2017 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB), 2017, pp. 1-6, doi: 10.1109/CIBCB.2017.8058546.

Sontakke, Sumedh & Lohokare, Jay & Dani, Reshul & Shivagaje, Pranav (2019) Classification of Cardiotocography Signals Using Machine Learning. Proceedings of the 2018 Intelligent Systems Conference (IntelliSys). 2019. Volume 2. 10.1007/978-3-030-01057-7_35.

Miao, Julia & Miao, Kathleen (2018) Cardiotocographic Diagnosis of Fetal Health based on Multi-class Morphologic Pattern Predictions using Deep Learning Classification. International Journal of Advanced Computer Science and Applications. 2018. 9. 1-11. 10.14569/IJACSA.2018.090501.

Garcia-Canadilla, Patricia & Sánchez Martínez, Sergio & Crispi, Fatima & Bijnens, Bart (2020) Machine Learning in Fetal Cardiology: What to Expect. Fetal Diagnosis and Therapy. 2020. 47. 1-10. 10.1159/000505021.

Tadele Debisa Deressa and Kalyani Kadam (2018) Prediction of Fetal Health State during Pregnancy: A Survey. International Journal of Computer Science Trends and Technology (IJCST).