Maternal health is an important issue that affects millions of women globally. Pregnancy and delivery difficulties are known to be preventable and result in the death of the majority of pregnant women. Early detection of maternal health risk factors can lead to better results for both the mother and the child. The goal of this study is to use clinical data to develop a machine-learning model that will classify risk factors for maternal health. In our work, we train the model using a dataset of patient records that includes information on medical history, demographics, and pregnancy outcomes. The most significant risk variables for maternal health were identified, and the effectiveness of many machine learning risk factor classification algorithms for mothers’ health was assessed. In this study, we categorize the risk factor levels using a variety of supervised learning algorithms, such as the K Nearest Neighbors Classifier, Decision Tree Classifier, Random Forest Classifier, GaussianNB Classifier, and SVM Classifier. We got the highest 98% accuracy for Random Forest and the lowest 91% accuracy for KNN 97% for Decision Tree and 94% and 93% for SVM and GaussianNB respectively. The investigation’s findings will provide significant new knowledge regarding the factors that increase the risk to maternal health. Using machine learning techniques, this study will also help with the classification of maternal health risk factors.