The health of women during pregnancy, childbirth, and the postnatal period is a critical aspect known as maternal health. Between 50% and 98% of maternal fatalities are due to direct obstetric factors such as bleeding, infection, complications from high blood pressure, uterine rupture, liver conditions, and anemia. The latest data from 2020 indicates a maternal mortality ratio of approximately 224 deaths per 100,000 live births. Current predictive models only offer limited effectiveness as they fail to fully integrate the prognostic and analytical dimensions present in extensive data sets, which include multiple risk factors related to maternal health. In the quest to harness large medical data sets for better prediction of diseases, data experts are testing various machine learning methods. This research scrutinized a range of algorithms such as K-Nearest Neighbors (KNN), Random Forest, Logistic Regression, Extreme Gradient Boosting (XGBoost), and Decision Trees. Upon evaluation, Logistic Regression was observed to have the lowest prediction accuracy at 59%, with Random Forest at 86%, KNN at 73%, and Decision Tree close by at 85% accuracy. The study identified XGBoost as the superior machine learning tool, demonstrating a remarkable 93% prediction accuracy.