Diarrheal disease remains one of the major health problems among toddlers in Indonesia. Environmental factors such as drinking water quality, sanitation, mothers’ hand hygiene, and immunization status play an important role in influencing the occurrence of diarrhea. This study aims to analyze the application of the C4.5 algorithm in developing a predictive model for diarrhea among toddlers using secondary data from a Public Health Center (Puskesmas), consisting of 200 records divided into 150 training data and 50 testing data. The analysis process was carried out through entropy calculation, information gain assessment, and decision tree construction to obtain classification patterns. The results showed that the C4.5 model achieved an accuracy of 92%, precision of 87.5%, recall of 87.5%, F1-score of 87.5%, and specificity of 94.12%. These values indicate that the C4.5 algorithm is capable of making predictions with a good level of accuracy and balance in detecting both positive and negative cases. This study contributes to the utilization of data mining, particularly the C4.5 algorithm, as a decision-support tool in the health sector for the prevention of diarrheal disease among toddlers.
Copyrights © 2025