<![CDATA[Pregnancy is an important phase that requires optimal health monitoring to prevent complications that are risky for both mother and fetus. The high maternal mortality rate in Indonesia emphasizes the importance of early detection of pregnancy risks. The use of machine learning offers an effective predictive approach to quickly and accurately identify pregnancy risks. This study aims to compare the performance of five machine learning algorithms, namely Logistic Regression, Decision Tree C4.5, Random Forest, Support Vector Machine, and Naive Bayes, using the Maternal Health Risk Dataset. The hold-out validation method with data sharing of 80% training data and 20% test data was used in this study. Model evaluation is conducted based on accuracy, precision, recall, and F1-score metrics. The results showed that Random Forest had the best performance with an accuracy of 93%, followed by Decision Tree at 93%, SVM at 82%, Logistic Regression at 76%, and Naive Bayes at 72%. Thus, Random Forest is rated as the most optimal algorithm in predicting pregnancy risk and potentially supporting the development of decision support systems for health workers. This research is expected to be the basis for the development of a machine learning-based decision support system to increase the effectiveness of health services for pregnant women.]]>
Copyrights © 2026
