Classification Of Outpatient Visit Status Walking at Dr. Zubir Mahmud Hospital Using Algoritma C4.5

Fikria, Putri
Dinata, Rozzi Kesuma
afrillia, Yesy

International Journal of Engineering, Science and Information Technology
Vol 5, No 3 (2025)

This study aims to classify the status of outpatient visits at RSUD Dr. Zubir Mahmud into three main categories, namely "Very Urgent", "Urgent", and "Not Urgent”, using the C4.5 algorithm. The web-based system uses the PHP programming language and MySQL database to ensure ease of implementation and efficient data management. The classification process is done by setting threshold parameters, calculating entropy, and the gain ratio to form an accurate and reliable decision tree. The results show that the C4.5 algorithm can classify patient visit data with a reasonably high accuracy rate, which is 93.75% for 2022 data and reaches 100% for 2023 data. In 2022 the “Very Urgent" category had 9 True Positives (TP); in 2023, the number remained consistent. However, in both years, there were also False Negatives in the same category, with 4 cases in 2022 and 5 cases in 2023. The "Urgent" and "Not Urgent" categories show suboptimal classification performance due to uneven data distribution, which causes the precision and recall values in these categories low. Model evaluation was conducted using evaluation metrics such as precision, recall, and F1 score. The evaluation results show that the model works very well in identifying high-priority categories, but further development is needed to improve classification in other categories. This system is expected to be a reliable tool in decision-making in health services, especially in determining the priority of patient services appropriately and efficiently. With further development, this system has the potential to be widely applied in various other hospitals.