Design and Develop An Early Detection System Application to Monitor Kidney Health in Pregnant Women

Abstract

Pregnancy is a physiological process that can become pathological if not well monitored. Kidney disease will increase the risk during pregnancy, namely preeclampsia, fetal growth restriction, and loss of maternal kidney function. Chronic kidney disease in pregnant women often goes undiagnosed. Kidney disease problems detected will worsen if not examined at the early signs and symptoms or delaying treatment for kidney disease. This study proves the effectiveness and accuracy of early detection systems for kidney health in pregnant women. In the design of this application, exploratory data analysis (EDA) and data visualization techniques are used, which will provide deeper insight into the distribution, trends and relationships between variables in the data which includes data on pregnant women, perceived symptoms and laboratory examination. From the results of the design of this early detection system application, it shows perfect performance of the model on the overall dataset with precision, recall, and F1-score scores all reaching 1.00 or 100% accuracy. The developed classification model shows outstanding performance. This success can be attributed to the selection of relevant features, effective data preprocessing, and the selection of the appropriate classification model.