Web-Based Expert System for Childhood Pneumonia Diagnostic and Management

Abstract

Abstract

This study focuses on developing a web-based expert system to diagnose children with pneumococcal infections. Pneumonia is the most common respiratory disease that causes death in children worldwide, and its diagnosis is challenging due to clinical symptoms similar to other respiratory diseases. As a result, doctors often request multiple tests before deciding, resulting in high costs and longer wait times. The web-based system developed in this study aims to assist doctors and patients in distinguishing between pneumonia and other diseases such as lung cancer, chronic bronchitis, and tuberculosis. The system takes symptoms such as fever, lack of appetite, cough, chills, haemoptysis, and chest pain as input and produces pneumonia as output. The triangular membership function was used to determine the membership level of both the fuzzy logic input and output. The Mandani max- min inference engine was used for logical reasoning, and the fuzzy output was converted back to crisp output in the defuzzification process. The system underwent four development stages: definition of a knowledge system, design, implementation, evaluation, and testing. The evaluation showed a sensitivity of 95%, specificity of 88%, and accuracy of 93% in diagnosing pneumococcal infections in children.