Prediksi Dini Penyakit Diabetes Pada Ibu Hamil Dengan Algoritma Random Forest

Abstrak

Diabetes in pregnant women, otherwise known as gestational diabetes, is a serious health condition that can negatively affect the mother and fetus. Early detection and appropriate intervention are essential to reduce the risk of complications during pregnancy and childbirth. This study aims to develop a prediction model that can detect the risk of diabetes in pregnant women using the Random Forest algorithm. The data used in this study included relevant clinical and demographic parameters of pregnant women, such as age, body mass index, family history, and laboratory test results. The Random Forest model was chosen because of its ability to handle complex data and provide accurate prediction results. The results of this study show that the model developed has an accuracy rate of 98% in predicting the risk of gestational diabetes. In addition, important features that contribute to diabetes risk prediction have also been identified, providing additional insights for medical practitioners in conducting risk evaluations. The implementation of this model is expected to help in efforts to prevent and manage gestational diabetes, thereby improving maternal and infant health.