Expert System for Early Detection of Thalassemia Disease Using Case-Based Reasoning Method

Thalassemia is a blood disorder characterized by abnormalities in globin chain formation. In Banyumas Regency, the prevalence of thalassemia continues to increase yearly, while detection processes are often delayed due to limited access to experts. This study aims to develop a web-based expert system for the early detection of thalassemia using the Case-Based Reasoning (CBR) method with the K-Nearest Neighbor (KNN) algorithm. The system is designed to help identify individuals who may carry the thalassemia gene trait, enabling faster and more accurate treatment. The system was tested using the black box method to ensure all features function properly across all user roles, including general users, administrators, and experts. Accuracy evaluation was conducted using a confusion matrix, achieving an accuracy rate of 95,23% based on 21 test data samples. The results indicate that this system provides highly accurate early detection and supports preventive efforts against thalassemia. Further development is recommended to create an Android-based application to enhance accessibility for the broader community. Additionally, continuous updates to the knowledge base are necessary to improve the system's accuracy and scope. This study is expected to contribute to the prevention and management of thalassemia, increase public awareness, and support better healthcare services in Indonesia