<![CDATA[Determining the health status of the fetus is a crucial aspect of pregnancy monitoring to reduce the risk of complications and increase the safety of the mother and baby. The K-Nearest Neighbors (KNN) method has been implemented as a classification technique in determining fetal health status based on cardiotocography (CTG) data. This study describes the use of the KNN algorithm to analyze various CTG parameters, including fetal heart rate and uterine contraction frequency, to classify fetal health status into three categories: normal, suspect, and pathologic. The implementation process involves collecting normalized data, selecting relevant features, and using the KNN algorithm with varying K values to determine the most optimal value. The research results show that the KNN method with the right K value can achieve high accuracy in classifying fetal health status, with accuracy reaching up to 89%. These findings indicate that KNN is an effective and reliable method in supporting medical personnel to make decisions based on CTG, which can ultimately improve the quality of maternal and infant health care. In addition, the implementation of this method is relatively simple and can be integrated into existing health systems without requiring large computing resources. Further research is recommended to compare the performance of KNN with other machine learning methods such as Support Vector Machine(SVM) and Random Forest to identify the best method in this context. The use of larger and more diverse data is also expected to increase the accuracy and generalization of the model in various clinical conditions.]]>
