Title: Expert System Design and Implementation for Medical Diagnostic Applications
Authors: Basel Midhat Mohaisen and Samy S. Abu-Naser
Volume: 9
Issue: 8
Pages: 85-94
Publication Date: 2025/08/28
Abstract:
The increasing demand for accurate and efficient medical diagnosis has highlighted the need for intelligent systems that can assist healthcare professionals in complex decision-making tasks. Knowledge-Based Expert Systems (KBES) offer a promising solution by emulating the reasoning capabilities of human experts through structured representations of medical knowledge and logical inference mechanisms. This paper presents the design and development of a rule-based expert system for medical diagnosis, aimed at supporting physicians in diagnosing common diseases based on patient symptoms and clinical findings. The proposed system comprises three core components: a knowledge base, an inference engine, and a user interface. The knowledge base contains a collection of production rules derived from medical experts, clinical guidelines, and peer-reviewed literature. These rules map combinations of symptoms and test results to possible diagnoses. The inference engine uses forward chaining reasoning to evaluate user inputs against the rules, allowing the system to infer one or more likely diagnoses. A user-friendly graphical interface facilitates the input of patient data and displays the diagnostic outcomes in a clear and interpretable format. To validate the system, several case studies involving common conditions such as diabetes, hypertension, and respiratory infections were tested. The results indicate a high level of agreement between the system's output and diagnoses provided by medical professionals, underscoring its potential as a reliable decision-support tool. This study also explores key challenges in developing KBES, including knowledge acquisition bottlenecks, rule conflict resolution, and system evaluation. Ultimately, the proposed system demonstrates how artificial intelligence and expert knowledge can be integrated to enhance clinical efficiency, reduce diagnostic errors, and provide scalable solutions for resource-limited settings.