Asian Journal of Research in Computer Science

This study focuses on the development of a rule-based expert system for diagnosing people with pneumonic infections. Pneumonia is the most common respiratory disease causing death worldwide, and its diagnosis is difficult due to clinical symptoms similar to other respiratory diseases. As a result, doctors often order multiple tests before making a decision, leading to high costs and longer wait times. The expert system developed in this study aims to help doctors and patients distinguish between pneumonia and other diseases such as cancer, chronic bronchitis and tuberculosis. The system takes symptoms such as fever, lack of appetite, cough, chills, hemoptysis and chest pain as input and produces pneumonia as output. The system has gone through four stages of development: definition of a knowledge system, design, implementation, evaluation and testing. The study is based on a dataset made up of 152 medical records including patients with respiratory symptoms similar to those of pneumonia. This data comes from hospital sources or medical databases, integrating information on medical history, chest imaging results and biological analyses. Validation of the system was carried out by comparing its performance to diagnoses made by specialists. The results indicate a diagnostic accuracy of 76%, demonstrating the effectiveness of the system in differentiating pneumonia from other respiratory conditions such as bronchitis, tuberculosis or pulmonary embolism. The study concludes that this rule-based expert system provides a promising tool to assist clinicians in the differential diagnosis of pneumonia, particularly in resource-limited settings where specialized medical expertise may be lacking. The Cohen's Kappa coefficient (κ\kappaκ) is approximately 0.76, indicating a substantial agreement between the expert system and the doctors. This suggests that the expert system performs well but still has room for improvement.