Title: An Expert System for Diagnosing Cold and Flu Diseases Using CLIPS
Authors: Mohammed. I. M. Al-Laham, Samy S. Abu-Naser
Volume: 10
Issue: 7
Pages: 21-29
Publication Date: 2026/07/28
Abstract:
Background: Expert systems represent one of the most successful applications of Artificial Intelligence (AI), particularly in the healthcare domain where they assist in diagnosis and decision-making processes. Respiratory illnesses such as Common Cold and Influenza are among the most prevalent diseases worldwide and often exhibit overlapping symptoms, making preliminary diagnosis a challenging task for non-specialists. Objectives: This study aims to design, implement, and evaluate a rule-based expert system using the CLIPS expert system shell for diagnosing Common Cold, Influenza (Flu), and Severe Flu. The proposed system seeks to provide preliminary diagnostic support and appropriate recommendations based on user-reported symptoms. Methods: The expert system was developed following the knowledge engineering methodology. Medical knowledge related to respiratory illnesses was collected from common diagnostic guidelines and transformed into IF-THEN production rules. The knowledge base was implemented using CLIPS, where user responses are represented as facts and processed through an inference engine to generate diagnoses and recommendations. The system interacts with users through a structured consultation process consisting of symptom-related questions. Results: Experimental evaluation was performed using multiple diagnostic scenarios representing different symptom combinations. The results demonstrated that the developed expert system successfully identified Common Cold, Influenza, and Severe Flu cases according to the entered symptoms. Furthermore, the system generated appropriate recommendations corresponding to each diagnosed condition, confirming the effectiveness of the implemented rule-based knowledge representation. Conclusion: The findings indicate that the proposed expert system is capable of providing consistent and reliable preliminary diagnoses for common respiratory illnesses. The study highlights the effectiveness of CLIPS and knowledge-based technologies in developing medical decision-support applications. Future enhancements may include expanding the knowledge base, incorporating uncertainty handling techniques, and developing a graphical user interface to improve usability.