OUTPATIENT LENGTH OF STAY (OLOS) ANALYSIS AT EDELWEIS HOSPITAL USING MACHINE LEARNING ALGORITHM

• Main Author: Ulfah, Halida
• Format: Theses
• Language: Indonesia
• Subjects: Manajemen umum
• Online Access: https://digilib.itb.ac.id/gdl/view/79968
• Institution: Institut Teknologi Bandung

Patient satisfaction is an essential indicator that must be taken into account. Patient satisfaction is influenced by a variety of factors, including the standard treatment received, the staff's initial attitude toward the patient, administrative processes, and the most common one is the the length of waiting time (LOS) experienced by the patient during the oupatient clinic service. The Indonesian Ministry of Health has set minimum standards for health services that must be met by all hospitals in Indonesia, namely a maximum of 60 minutes for outpatient waiting time which is defined from the patient arriving at the hospital until receiving treatment from a doctor. However, this standard does not provide information regarding the outpatient waiting time (OLOS) which is defined from the time the patient arrives at the hospital until the patient leaves the hospital. With the increasing competition in the healthcare industry and patients' demands for higher-quality care, hospitals are focusing more on enhancing their quality from a clinical and management perspective. Therefore, the hospital management itself sets the operational standards for the OLOS. As a result, the Edelweis Hospital in Bandung establishes a 2-hour maximum waiting period for outpatient services. Providing accurate information about OLOS may increase patient satisfaction by reducing uncertainty. However, effective methods to predict the length of stay for outpatients (OLOS) in Pediatric Clinics are seldom known. This study's goal is to design a prediction model for OLOS based on patient characteristics and several other clinical attributes. The data was obtained from the IT division at Edelweis Hospital with a total data is 17,167 and 6,172 could be analysis further. By identifying the attributes that affected OLOS, the model will help hospital make relevant decisions. We used machine learning algorithms such as random forest, decision tree, k-nearest neighbor (kNN), adaboost, and gradient boosting to design prediction models for OLOS. From the validation set, random forest has the highest accuracy rate with a value of 99.3% Furthermore, machine learning models were used to determine the importance of attributes. These models could eventually be used alongside real-time IT system data to provide accurate real-time estimates of OLOS at the Pediatric Clinic.