This research aims to conduct a comparative analysis of machine learning algorithms for classifying the risk levels of maternal health. With a focus on the significance of identifying and classifying health risks for pregnant women, this study applies supervised learning methods employing Naïve Bayes, Decision Tree, and K-Nearest Neighbors algorithms. Utilizing the "Maternal Health Risk" dataset from UCI Machine Learning, the research is conducted on Google Colaboratory using Python. The results indicate that the Decision Tree algorithm achieves the highest accuracy rate at 90%, surpassing K-Nearest Neighbors (86%) and Naïve Bayes (65%). Consequently, Decision Tree emerges as the preferred choice for predicting maternal health risks, offering the potential for enhanced care and monitoring.