Prediction of Maternal Health Risk with Traditional Machine Learning Methods

Year 2023, , 16 - 23, 30.06.2023

Hursit Burak Mutlu , Fatih Durmaz , Nadide Yücel , Emine Cengil , Muhammed Yıldırım

https://doi.org/10.46572/naturengs.1293185

Cited By: 3

Abstract

In risky pregnancy, various diseases such as heart, lung, kidney, high blood pressure, diabetes and liver that pregnant women have before may aggravate the expectant mother's condition during pregnancy. By analyzing medical parameters such as maternal age, heart rate, blood oxygen level, blood pressure, body temperature, and the values corresponding to these parameters, information on risk intensity can be estimated for some patients. It is possible to reduce such pregnancy-related complications by classifying risk factors early in symptoms. It is possible to benefit from machine learning methods in determining maternal risk health. Therefore, in this study, six different machine learning methods were used to determine maternal risk health. The results obtained in these methods were compared with each other and it was observed that the most successful method in estimating maternal risk health was Decision Tree. The accuracy value obtained in the Decision Tree method was 89.16%. The lowest accuracy rate among the methods used in the paper was obtained in the k-nearest neighbors (KNN) method with 68.47%.

Keywords

Artificial Intelligence, Classifiers, KNN, Machine Learning, Maternal Health

References

• Pawar, L. et al. (2022) A Robust Machine Learning Predictive Model for Maternal Health Risk. in 2022 3rd International Conference on Electronics and Sustainable Communication Systems (ICESC). IEEE. 882-888.
• Varshavsky, J., et al. (2020) Heightened susceptibility: A review of how pregnancy and chemical exposures influence maternal health. Reproductive toxicology, 92: 14-56.
• Umoren, I., et al., Modeling and Prediction of Pregnancy Risk for Efficient Birth Outcomes Using Decision Tree Classification and Regression model.
• Ahmed, M. and M.A. Kashem. IoT based risk level prediction model for maternal health care in the context of Bangladesh. in 2020 2nd International Conference on Sustainable Technologies for Industry 4.0 (STI). 2020. IEEE.
• Ahmed, M., et al. Review and analysis of risk factor of maternal health in remote area using the internet of things (IoT). in InECCE2019: Proceedings of the 5th International Conference on Electrical, Control & Computer Engineering, Kuantan, Pahang, Malaysia, 29th July 2019. 2020. Springer.
• Rai, S.K. and K. Sowmya (2018) A review on use of machine learning techniques in diagnostic health-care. Artificial Intelligent Systems and Machine Learning, 10(4): 102-107.
• Quinlan, J.R. (1987) Simplifying decision trees. International journal of man-machine studies, 27(3): 221-234.
• Ke, G., et al. (2017) Lightgbm: A highly efficient gradient boosting decision tree. Advances in neural information processing systems, 3149–3157.
• Hancock, J.T. and T.M. Khoshgoftaar (2020) CatBoost for big data: an interdisciplinary review. Journal of big data, 7(1): 1-45.
• Pal, M. (2005) Random forest classifier for remote sensing classification. International journal of remote sensing, 26(1): 217-222.
• Natekin, A. and A. Knoll (2013) Gradient boosting machines, a tutorial. Frontiers in neurorobotics, 7: 21.
• Keller, J.M., M.R. Gray, and J.A. Givens (1985) A fuzzy k-nearest neighbor algorithm. IEEE transactions on systems, man, and cybernetics, SMC-15(4): 580-585.
• https://www.kaggle.com/datasets/csafrit2/maternal-health-risk-data?resource=download.
• Yildirim, M., et al. (2023) Automatic Classification of Particles in the Urine Sediment Test with the Developed Artificial Intelligence-Based Hybrid Model. Diagnostics, 13(7): 1299.
• Özbay, F. A., & Özbay, E. (2023). An NCA-based Hybrid CNN Model for Classification of Alzheimer’s Disease on Grad-CAM-enhanced Brain MRI Images. Turkish Journal of Science and Technology, 18(1), 139-155.