Machine learning models for predicting caesarean section delivery among women in Ethiopia

Abstract

The rising rates of Cesarean Sections deliveries globally pose significant challenges to maternal and neonatal health. Accurate prediction of Cesarean Sections delivery is critical for timely clinical decision-making, especially in resource-limited settings such as Ethiopia. This study leverages machine learning classification techniques to predict cesarean section deliveries among Ethiopian women, aiming to identify key risk factors and support interventions that improve maternal and neonatal outcomes. A cross-sectional study was conducted using data from the 2019 Ethiopian Demographic and Health Survey (EDHS). Data processing and analysis were performed using Python (version 3.9). Machine learning algorithms including Random Forest (RF), Decision Tree (DT), Logistic Regression (LR), Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), and K-Nearest Neighbor (KNN), were implemented. Model performance was evaluated using standard metrics such as area under the ROC curve (AUC), accuracy, precision, recall, and F1-score. Among the developed models, Random Forest (RF) demonstrated the best performance, achieving an accuracy of 94.44% and an AUC of 97.99%. Overall, Random Forest proved to be the most reliable model for predicting cesarean section deliveries in this dataset. Random Forest demonstrated superior predictive performance in identifying women at risk of Cesarean Sections delivery in Ethiopia. These findings highlight the potential of machine learning techniques to support data-driven decision-making in maternal healthcare and to guide interventions aimed at optimizing delivery outcomes.