Socio-Demographic Predictors of Maternal Health-Related Outcomes: A Systematic Review of Machine Learning Studies in Sub-Saharan Africa
Keywords:
Machine learning, maternal health, socio-demographic determinants, maternal healthcare outcomes, Sub-Saharan AfricaAbstract
Each year two hundred and sixty thousand maternal deaths, seventy percent of these deaths happen in Sub-Saharan region. Maternal death continues to be a persistent health issue in Africa despite improvements in maternal healthcare services. Advancements in machine learning technology provide opportunities to predict adverse maternal health outcomes, thereby supporting timely and preventive interventions. While much research has been done to identify the causes of maternal deaths, fewer studies have paid attention to the use of socio-demographic factors in predicting maternal healthcare outcomes. This review aimed to examine evidence on how socio-demographic determinants and machine learning have been applied to predict maternal health outcomes in Sub-Saharan Africa. Electronic databases and scholarly search engines were used to select studies published between January 2019 and June 2026, selected articles included in the review were studies conducted within Sub-Saharan region countries that utilized machine learning algorithms to evaluate how socio-demographic factors affect maternal health outcomes. Frequently used socio-demographic factors associated with maternal healthcare outcomes included household wealth, education, antenatal care utilization, residence place and media exposure. The review noted that use of explainable artificial intelligence such as Shapley Additive exPlanations (SHAP) and association rule mining were used to enhance model interpretability. However, methodological inconsistencies in handling class imbalance and validation procedures were identified as challenges that affect the accuracy of reported models. While socio-demographic determinants provide useful predictive information for maternal healthcare outcomes, particularly in low income settings, future studies should improve methodological consistency and incorporate underrepresented third-delay factors such as quality of care, availability of skilled personnel, medicines, referral efficiency and facility readiness, to support more comprehensive maternal healthcare prediction.
References
Aikpitanyi, J. (2026). Access alone is not enough: Rethinking maternal health in sub-Saharan Africa. African Journal of Reproductive Health, 30(3), 9–12. https://doi.org/10.29063/ajrh2026/v30i3.1
Al Mashrafi, S. S., Tafakori, L., & Abdollahian, M. (2024). Predicting maternal risk level using machine learning models. BMC Pregnancy and Childbirth, 24, Article 820.
Baykemagn, N. D., Taye, E. A., Melaku, M. S., Yehuala, T. Z., Tewelgne, M. F., Arage, F. G., & Zegeye, A. T. (2025). Predicting delayed antenatal care initiation among pregnant women in East Africa: Using machine learning algorithms. Frontiers in Global Women’s Health, 6, 1488391.
Campbell, M., McKenzie, J. E., Sowden, A., Katikireddi, S. V., Brennan, S. E., Ellis, S., Hartmann Boyce, J., Ryan, R., Shepperd, S., Thomas, J., Welch, V., & Thomson, H. (2020). Synthesis without meta analysis (SWiM) in systematic reviews: Reporting guideline. BMJ, 368, l6890. https://doi.org/10.1136/bmj.l6890
Kassaw, A. K., Kidie, A. A., Tesfa, N. A., Mislu, E., Yimer, A., Hailu, M., Yesuf, H. A., Ayal, B. G., Geto, A. K., & Feleke, S. F. (2025). Optimizing machine learning models for predicting health service access and determinants among pregnant women in rural Ethiopia. Scientific Reports, 15(1), 40559.
Ngaji, C. O. (2022). Predicting antenatal care (ANC) visits using machine learning algorithms [Master's thesis, University of Nairobi].
Ngusie, H. S., Tesfa, G. A., Taddese, A. A., Enyew, E. B., Alene, T. D., Abebe, G. K., Walle, A. D., & Zemariam, A. B. (2024). Predicting place of delivery choice among childbearing women in East Africa: A comparative analysis of advanced machine learning techniques. Frontiers in Public Health, 12, 1439320.
Taye, E. A., Woubet, E. Y., Hailie, G. Y., Arage, F. G., Zerihun, T. E., Zegeye, A. T., Zeleke, T. C., & Kassaw, A. T. (2025). Application of the random forest algorithm to predict skilled birth attendance and identify determinants among reproductive-age women in 27 Sub-Saharan African countries; machine learning analysis. BMC Public Health, 25(1), 901.
Tesfaye, B., Atique, S., Azim, T., & Kebede, M. M. (2019). Predicting skilled delivery service use in Ethiopia: Dual application of logistic regression and machine learning algorithms. BMC Medical Informatics and Decision Making, 19(1), 209.
Thaddeus, S., & Maine, D. (1994). Too far to walk: Maternal mortality in context. Social Science & Medicine, 38(8), 1091–1110.
World Health Organization. (2025). Trends in maternal mortality estimates 2000 to 2023: Estimates by WHO, UNICEF, UNFPA, World Bank Group and UNDESA/Population Division
Zegeye, A. T., Tilahun, B. C., Fekadie Tewelgne, M., Addisu, E., Wassie, B., Alelign, B., Sharew, M., Baykemagn, N. D., Kebede, A., & Yehuala, T. Z. (2025). Predicting home delivery and identifying its determinants among women aged 15–49 years in sub-Saharan African countries using a Demographic and Health Surveys 2016–2023: A machine learning algorithm. BMC Public Health, 25(1), 302.
