Francisca A. Egbokhare

Maternal mortality continues to pose a significant public health challenge in Sub-Saharan Africa, with Nigeria ranking among the countries with the highest burden. The death of women during their reproductive years not only disrupts family structures and causes emotional distress but also places an increased strain on healthcare systems and impedes national economic and developmental progress. In alignment with the United Nations Sustainable Development Goals (SDGs), particularly the goal focused on reducing maternal mortality, this study investigates the application of Artificial Intelligence (AI) in maternal healthcare through the development of a predictive ensemble model for maternal mortality in Delta State, Nigeria. The objective was to accurately classify maternal health risks, enabling the early identification of high-risk pregnancies and facilitating timely clinical interventions that can reduce preventable maternal deaths. Maternal health data were collected from three healthcare centers across Delta State, Nigeria. Nine supervised machine learning algorithms were employed, including Linear Support Vector Machine (SVM), Gaussian Naïve Bayes, Multilayer Perceptron (MLP), Decision Tree, Random Forest, Gradient Boosting Decision Tree (GBDT), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Categorical Boosting (CatBoost).