<![CDATA[Pregnancy complications remain a major cause of high maternal and infant morbidity and mortality rates in various countries. Delays in detecting complications such as preeclampsia, gestational diabetes, preterm labor, and hypertensive disorders of pregnancy can lead to conditions that threaten the safety of both the mother and the fetus. The development of Artificial Intelligence (AI) technology provides opportunities to improve early detection capabilities through rapid and accurate clinical data analysis. This study aims to develop and evaluate an AI system for early detection of pregnancy complications using a Hybrid Research and Development (H&R) design. The research stages include needs analysis, data collection, model development, system validation, and prototype implementation. The data used comes from medical records of pregnant women, including age, blood pressure, body mass index, blood glucose levels, gestational age, and history of previous complications. Several machine learning algorithms were tested, namely Random Forest, Support Vector Machine, Decision Tree, Logistic Regression, and Artificial Neural Network. The results showed that the Random Forest algorithm provided the best performance with an accuracy rate of 92%, sensitivity of 94%, and specificity of 90%. The most influential variables in prediction were blood pressure, history of preeclampsia, and body mass index. The system implementation demonstrated high user acceptance, as it helped healthcare workers identify high-risk pregnant women more quickly and accurately. Therefore, the application of AI has the potential to become an effective clinical decision support system for improving the quality of antenatal care and supporting efforts to reduce maternal and infant mortality.]]>
Copyrights © 2025
