Implementation of the Bayesian Network Algorithm to Predict Chronic Diseases Using Electronic Medical Record Data at UPTD RSD Besemah, Pagar Alam City

Abstract

Chronic diseases are one of the leading causes of death in Indonesia and around the world. Early detection of chronic diseases poses a significant challenge for healthcare facilities, particularly in resource-limited areas such as UPTD RSD Besemah, Pagar Alam City. This study aims to implement the Bayesian Network algorithm as a method for predicting chronic diseases based on patients' electronic medical record (EMR) data. The Bayesian Network method was chosen due to its ability to model causal relationships between variables and its robustness in handling incomplete data. The data used in this research consists of secondary data in the form of patient medical records, with attributes including age, gender, medical history, laboratory results, and lifestyle factors. The research process involves data collection, preprocessing, Bayesian network structure formation, and model performance evaluation using accuracy, precision, and recall metrics. The results indicate that the Bayesian Network model is capable of delivering high prediction accuracy for chronic diseases such as diabetes mellitus, hypertension, and heart disease. The implementation of this predictive system is expected to assist medical personnel in clinical decision-making and enhance the effectiveness of preventive healthcare services.