Title: Design and Development of a Clinical Diagnosis Expert System
Authors: Wesam H. Ashour and Samy S. Abu-Naser
Volume: 9
Issue: 8
Pages: 154-158
Publication Date: 2025/08/28
Abstract:
Diagnostic errors remain a significant challenge in healthcare worldwide, contributing to delayed treatment, unnecessary costs, and avoidable mortality. In many low-resource settings, the shortage of medical specialists exacerbates these challenges. This research presents the design and development of a Knowledge-Based Expert System (KBES) for clinical diagnosis, focusing on common diseases such as diabetes, hypertension, respiratory infections, and gastrointestinal disorders. The system employs rule-based reasoning with forward-chaining inference, enabling transparent and explainable diagnostic outcomes. A structured knowledge base was developed using IF-THEN production rules derived from medical guidelines, textbooks, and expert consultations. The system was implemented in Python using an expert rule engine and tested with 30 simulated patient cases. Results demonstrated an accuracy rate of 87% compared to diagnoses made by licensed physicians. In addition, the system provides a justification facility to enhance trust and transparency, which is critical in medical decision support. This study demonstrates the feasibility and effectiveness of knowledge-based systems in supporting healthcare decision-making, particularly in resource-constrained environments. The findings highlight the ongoing relevance of rule-based AI systems, especially where interpretability is crucial. Future directions include expanding the disease coverage, integrating uncertainty handling, and conducting clinical trials for real-world validation.