PREDICTION OF DELIVERY METHOD USING DECISION SUPPORT SYSTEM AND DECISION TREE C4.5 ALGORITHM

Abstract

Errors in predicting the method of delivery are undesirable. Therefore, a prediction system is needed that can be used to predict the method of delivery as an option in the process of making decisions about the method of delivery so that prediction errors can be avoided and the selection of the right way of handling for patients can be avoided, thus avoiding risks in medical treatment. Caesarean section is an action taken to solve problems that occur in the delivery process that cannot be resolved normally. Every delivery has risks for both the mother and the fetus, namely the risk of complications to the risk of death. This study aims to develop a prediction model for the method of delivery in pregnant women using the C4.5 decision tree algorithm. The data used in this study are historical data from the medical records of pregnant women which include factors such as the mother's age, previous pregnancy history, and the health conditions of the mother and fetus. The C4.5 decision tree algorithm is used to build a prediction model based on these data. The most influential factors in predicting the method of delivery are the mother's age and previous pregnancy history. With this prediction model, it is expected to help medical personnel in making the right decisions regarding the method of delivery for pregnant women. The application of the waterfall method in system development ensures that the stages of system development are carried out in a structured and organized manner. The results of the study using Rapidminer software with 440 data obtained an accuracy of 90.23%.

Keywords: Predictions; algorithm; accuracy; labor; Decision Tree C4.5.