Application of Decision Trees for Predicting High-Risk Pregnancies at the Sukarame Community Health Center

Abstract

High-risk pregnancy remains one of the major causes of maternal and infant morbidity and mortality, particularly in developing countries. Early identification of pregnancy risks at the primary healthcare level is essential to improve maternal healthcare services and reduce pregnancy complications. However, at the Sukarame Community Health Center, the identification of high-risk pregnancies is still conducted manually and relies heavily on subjective assessment by healthcare workers. Although medical record data of pregnant women are available, the data have not been optimally utilized for systematic risk prediction and classification. This study aims to implement the Decision Tree algorithm to predict high-risk pregnancies using medical record data from pregnant women at the Sukarame Community Health Center. The study applies a quantitative approach using secondary data consisting of maternal age, blood pressure, hemoglobin levels, pregnancy history, and clinical symptoms. The research process includes data collection, preprocessing, classification modeling using the Decision Tree algorithm, and evaluation of model performance using accuracy, precision, and recall metrics. The results indicate that the Decision Tree algorithm is capable of classifying pregnancy risks into low, moderate, and high-risk categories in a structured and objective manner. The resulting model generates interpretable decision rules that can assist healthcare workers in conducting early detection and intervention for high-risk pregnancies. Furthermore, the implementation of the web-based prediction system improves efficiency in processing patient data and reduces subjectivity in pregnancy risk assessment. Therefore, the proposed system can support data-driven decision-making and contribute to improving the quality of maternal healthcare services at the primary healthcare level.