Abstract: Pregnancy is a critical phase in a woman's life that demands increased medical attention and care due to its vulnerability. Throughout this period, various irregularities might occur, and if not detected or treated promptly, they can result in severe consequences. These irregularities, known as "pregnancy complications," encompass a range of health issues arising from physiological changes during gestation, posing risks to the mother's well-being during pregnancy, delivery, and the postpartum period. This study aims to predict current health issues experienced by pregnant women using two distinct classification algorithms: the C4.5 decision tree and the Naive Bayes Classification Algorithm. Widely used in data mining for classification and prediction tasks, these algorithms analyze data from pregnant women at different stages of pregnancy to anticipate their present health status and related complications. The research strives to determine the superior algorithm for forecasting pregnant women's health conditions and associated complications. Applying these classification techniques to pregnancy data enables the assessment of health risks, potentially reducing maternal and fetal mortality rates
Keywords: Pregnancy Complications, C4.5 Decision Tree, Naïve Bayes Classification Algorithms, Fetal mortality rates, Physiological changes
Copyright Form