By analyzing maternal age, heart rate, blood oxygen level, blood pressure, and body temperature, it has the potential to evaluate the risk complexity for certain patients. Early identification and classification of risk variables can successfully prevent pregnancy-related issues by reducing the number of errors. Maternal risk analysis can improve prenatal care, improve mother and baby health, and optimize healthcare resources by identifying misclassified observations using machine learning algorithms such as LDA, QDA, KNN, Decision Tree, Random Forest, Bagging, and Support Vector Machine, all of which have a significant impact on maternity health risk assessment. The split validation technique was applied, using 800 observations for training and 214 for testing. In addition, the most dependable model was determined using a 10-fold cross-validation technique. The suggested model outperforms all others in terms of accuracy and efficiency, with an accuracy score of 86.13% for the support vector machine using a 10-fold cross validation technique. The purpose of this research is to use machine learning techniques to estimate the level of intensity of maternal health concerns by employing a classification strategy in the risk factor analysis.