<![CDATA[Caesarean delivery is a medical procedure performed under specific conditions to reduce risks for both mother and baby. However, the increasing rate of caesarean deliveries, which is not always based on medical indications, highlights the need to systematically understand the factors influencing delivery methods. This study aims to explore the relationship between clinical variables of pregnant women and delivery methods using a data mining approach based on Decision Tree and Random Forest algorithms. The dataset consists of secondary data collected from three primary healthcare centers (Puskesmas), namely Mranti, Banyuurip, and Bayan, with a total of 390 records. The study follows the Knowledge Discovery in Database (KDD) framework, including data selection, preprocessing, transformation, dataset splitting, handling class imbalance using Synthetic Minority Over-sampling Technique (SMOTE), modeling, and evaluation. The results show that the model achieved an accuracy of 88%, precision of 58.82%, recall of 66.67%, and an F1-score of 62.50%. Although the accuracy appears relatively high, the model’s performance in identifying caesarean cases remains moderate. This indicates that the model is more effective in classifying the majority class than the minority class. This study highlights that data mining applied to primary healthcare data can provide valuable insights for early pattern identification. However, the obtained results are not sufficient for direct clinical decision-making. Future research with larger datasets and more adaptive methods is required to improve model performance.]]>
Copyrights © 2026
