<![CDATA[Schizophrenia is a chronic mental disorder that often requires inpatient care, so an increase in the number of patients can lead to limited bed capacity in psychiatric wards. This study aims to classify the length of hospital stay for schizophrenia patients to support room requirement planning at RSUD Muyang Kute using the C4.5 algorithm optimized with Particle Swarm Optimization (PSO). The dataset consists of 657 medical records of inpatient schizophrenia cases from February 2023 to March 2025, categorized into three length-of-stay classes: short (1–5 days), medium (6–10 days), and long (>10 days). The C4.5 algorithm is used to construct a decision tree model based on historical data, while PSO is employed as an optimization method to improve the model configuration. The evaluation uses classification accuracy and Mean Absolute Percentage Error (MAPE) for room demand estimation. The results show that both the C4.5 and C4.5–PSO models achieve similarly high accuracy on the test data, while the manual MAPE calculation for room demand estimation yields a value of 52.66%. In contrast, the MAPE calculated by the system is 0.00% in the test scenario because all classes in the test data are correctly predicted. The web-based decision support system developed using Python and Streamlit is able to automatically provide predictions of length of stay and estimates of the required number of psychiatric beds at RSUD Muyang Kute.]]>
Copyrights © 2026
