Maternal mortality remains a critical challenge in Sub-Saharan Africa, with Nigeria ranking among the countries with the highest rates. The loss of women in their reproductive years destabilizes families causing emotional trauma, places additional strain on healthcare systems, and has profound economic and national developmental consequences. As a result, one of the United Nations Sustainable Development goals (SDGs) is targetted at reducing maternal mortality and morbidity at all cost. This study explores the application of Artificial Intelligence (AI) in healthcare through the development of a predictive ensemble model to classify maternal health risks as identifying high risk pregnancies can inform timely clinical decision making that mitigates maternal mortality. Maternal health dataset was sourced from three (3) health centers in Delta State, Nigeria.. Nine supervised machine learning classifiers were utilized, including Linear Support Vector Machine, Gaussian Naïve Bayes, Multilayer Perceptron, Decision Tree, Random Forest, Gradient Boosting Decision Tree, Extreme Gradient Boosting, Light Gradient Boosting Machine, and Categorical Boosting. To enhance predictive performance, the classifiers were combined in an ensemble model. Results showed that the Gradient Boosting Decision Tree achieved the highest accuracy at 90% before upsampling and Random Forest achieved an accuracy of 97% at upsampling. The lowest-performing classifier was Linear Support Vector Machine before and after upsampling. The ensemble model surpassed all individual classifiers, achieving 98% accuracy and precision and over 1% increase in accuracy after upsampling. This study highlights the potential of AI-driven predictive models to optimize healthcare resources and improve maternal health outcomes in Delta State, Nigeria.
References
Ahmed, M. (2020). Maternal health risk. UCI Machine Learning Repository. https://doi.org/10.24432/C5DP5D
Dawodi, M., Wada, T., & Baktash. J. A. (2020). Applicability of ICT, data mining and machine learning to reduce maternal mortality and morbidity: Case study Afghanistan. International Information Institute, 23(1), 33-45.
Gomez-Jemes, L., Oprescu, A. M., Chimenea-Toscano, A., Lutgardo, G., & Romero-Tornero, M. (2022). Machine learning to predict pre-eclampsia and uterine growth restriction in pregnant women. Electronics, 11(19), 3240. https://doi.org/10.3390/electronics11193240
Izugbara, C. O., Wekesah, F. M. & Adedini, S. A. (2016). Maternal health in Nigeria: A situation update. African Population and Health Research Centre. http://dx.doi.org/10.13140/RG.2.1.1291.9924
James, I., & Osubor, V. (2025). Machine learning evidence towards the eradication of malria burden: A scoping review. Applied Computer Science, 21(1), 46-69. https://doi.org/10.35784/acs_6873
Jayatilake, S. M., & Ganegoda, G. (2021). Involvement of machine learning tools in healthcare decision making. Hindawi Journal of Healthcare Engineering, 2021(1), 679512. https://doi.org/10.1155/2021/6679512
Khadka, N. (2024). How stacking technique boost’s machine learning model’s performance. Retrieved September 23, 2024 from https://dataaspirant.com/stacking-technique
Kopanitsa, G., Metsker, O., Paskochev, D. &, Greschischeva, S. (2021). Identification of risk factors and prediction of sepsis in pregnancy using machine learning. Procedia Computer Science, 193, 393-401. https://doi.org/10.1016/j.procs.2021.10.040
Machoron, J. J. E., Inbaraj, C. N., & Jeng, X. A. (2022). A semi-supervised machine learning approach in predicting high-risk pregnancies in the Philippines. Diagnostics, 12(11), 2782. https://doi.ord/10.3390/diagnostics/2112782
Mashrafi, S. S. A., Tafakori, L., & Abdollahian, M. (2024). Predicting maternal risk levels using machine learning models. BMC Pregnancy and Child Health, 24, 820. https://doi.org/10.1186/s12884-024-07030-9
Kalirane, M. (2024). Bagging, boosting and stacking: Ensemble learning in ml models. Analitics Vidhya. https://www.analyticsvidhya.com/blog/2023/01/ensemble-learning-methods-bagging-boosting-and-stacking/
Mboya, I. B., Mahande, M. J., Mohanad, M., Obure, J., & Mwambi, H. G. (2020). Prediction of perinatal death using machine learning models: A birth registry-based cohort study in northern tanzania. British Medical Journal Open, 10(10), e040132. https://doi.org/10.1136/bmjopen-2020-040132
Mienye, D. I., & Sun, Y. (2022). A survey of ensemble learning: Concepts, algorithms, applications and prospects. IEEE Access, 10, 99129-99149. https://doi.org/10.1109/ACCESS.2022.3207287
Mondal, S., Nag, A., Barman, A. K., & Karmakar, M. (2023). Machine-learning based maternal health risk prediction for IoMT framework. International Journal of Experimental Research and Review, 32, 145-159. https://doi.org/10.52756/ijerr.2023.v32.012
Mustamin, N. F., Aziz, F., Firmansyah, & Ishak, P. (2023). Classification of maternal health risk using three models Naïve Base method. Indonesian Journal of Computing and Cybernetics Systems,17(4), 395-404. https://doi.org/10.22146/ijccs.84242
Mutlu, H. B., Yucel, N., Durmaz, F., Cengil, E., & Yildirim, M. (2023). Prediction of maternal health risk with traditional machine learning methods. MTU Journal of Engineering and Natural Sciences, 4(1), 16-23. https://doi.org/10.46572/naturengs.1293185
Nirmala, & Kambili, R. S. (2023). Maternal risk level prediction using ensemble model. International Journal of Creative Research Thoughts, 11(3),916-920.
O’Neil, A. (2023). Total population in Nigeria from 2011 to 2021, by Gender (in millions). Statista. https://www.statista.com/statistics/967908/total-population-of-nigeria-by-gender/#:~:text=This%20statistic%20shows%20the%20total,to%20approximately%20107.83%20million%20inhabitants
Ogallo, W., Speakman, S., Akinwande, V., Vashrey, R. K., Walcott-Bryant, A., Wayua, C., Weldermarian, K., Mershon, C., & Orobaton, N. (2020). Identifying factors associated with neonatal mortality in sub-saharan Africa using machine learning. medRxiv. https://doi.org/10.1101/2020.10.14.20212225
Okpono, J., Asedegbega, J., & Sanyaolu, T. O. (2024). Enhancing the predictive accuracy of machine learning models for project management challenges: A comparative study of advanced techniques for handling imbalanced data. Technix International Journal for Engineering Research, 11(9), 99129-99137. http://dx.doi.org/10.5281/zenodo.13817083
Olonade, O., Olawande, T. I., Alabi, O. J. & Imhonopi, D. (2019). Maternal mortality and maternal healthcare in nigeria: Implications for socio-economic development. Open Access Macedonian Journal of Medical Sciences, 7(5), 849-855. https://doi.org/10.3889/oamjms.2019.041
Rosser, J. I., Aluri, K. Z., Kempinsky, A., Shannon, R., & Bendavid, E. (2022). The effect of healthcare worker density on maternal health service utilization in sub-saharan Africa. The American journal of tropical medicine and hygiene, 106(3), 939-944. https://doi.org/10.4269/ajtmh.21-0727
Togunwa, T. O., Babatunde, A. O., & Abdullah, K. K-u-R. (2023). Deep hybrid model for maternal health risk classification in pregnancy: synergy of ann and random forest. Frontiers in Artificial Intelligence, 6. 1213436. https://doi.org/10.3389/frai.2023.1213436
United Nations Country Office in Nigeria.(2015). Delta State Development Performance. Health Sector Report, 1991 - 2013 https://www.undp.org/sites/g/files/zskgke326/files/migration/ng/UNDP_NG_DeltaState_Health_2015.pdf
Wahl, B., Cossy-Gantner, A., Germann, S., & Schwalbe, N. R. (2018). Artificial intelligence (AI) and global health: How can AI contribute to health in resource-poor settings?. British Medical Journal Global Health 2018, 3, e000798. https://doi.org/10.1136/bmjgh-2018-000798
World Health Organisation. (2019). Maternal Health. http://www.who.int/maternal-health/en/
World Health Organisation. (2023). Trends in maternal mortality 2000 to 2017: Estimates by WHO, UNICEF, UNFPA, World Bank Group and the United Nations Population Division: Executive summary. http://apps.who.int/iris/handle/10665/327596