Title: Developing an Expert System for Diabetes Diagnosis Using CLIPS
Authors: Qutaiba Jomah Mohammed Alnajjar , Samy S. Abu-Naser
Volume: 10
Issue: 7
Pages: 49-59
Publication Date: 2026/07/28
Abstract:
Diabetes mellitus is one of the most prevalent chronic diseases worldwide, requiring early detection and continuous monitoring to reduce the risk of severe health complications. Artificial Intelligence (AI)-based medical decision support systems have demonstrated significant potential in assisting healthcare professionals and improving accessibility to preliminary medical assessment. Expert systems, as knowledge-based AI applications, provide decision-making capabilities by representing expert knowledge through logical rules and inference mechanisms. This paper presents the design and implementation of an intelligent expert system for preliminary diabetes diagnosis using the CLIPS expert system shell. The proposed system utilizes a knowledge base containing diabetes-related symptoms and medical decision rules represented using IF-THEN production rules. The inference engine analyzes user-provided information, evaluates symptom combinations, and generates a possible diabetes assessment with recommendations. The system development process includes knowledge acquisition, knowledge representation, rule development, user interaction design, and system evaluation. The proposed system was tested using multiple hypothetical patient cases to evaluate its ability to produce consistent diagnostic recommendations. Experimental results indicate that the system successfully applies the predefined medical rules and provides rapid preliminary assessments. The developed expert system demonstrates the effectiveness of rule-based artificial intelligence approaches in supporting healthcare decision-making. Although the system is not intended to replace professional medical diagnosis, it can serve as an educational and preliminary screening tool. Future improvements may include integration with machine learning techniques, larger medical datasets, and advanced user interfaces.