DEPLOYING THE EXPERT SYSTEM FOR TROPICAL DISEASE DIAGNOSIS IN RESOURCE-LIMITED SETTINGS

Tropical diseases such as malaria, dengue, chikungunya, and typhoid continue to pose major public health challenges in resource-limited regions due to inadequate access to skilled healthcare professionals and diagnostic infrastructure. To address this gap, this paper presents the design and deployment of an intelligent Expert System for Tropical Disease Diagnosis that leverages rule-based reasoning and knowledge engineering to support clinical decision-making in low-resource environments. The system integrates patient symptoms, epidemiological data, and diagnostic rules derived from domain experts to provide probabilistic disease predictions and treatment recommendations. A lightweight, mobile-compatible architecture ensures usability in remote areas with limited internet connectivity. The inference engine employs forward chaining for real-time diagnosis, while a locally hosted knowledge base enables offline operation and easy scalability. Field evaluation results demonstrate that the proposed expert system achieves over 90% diagnostic accuracy, significantly reducing the burden on medical personnel and improving early disease detection rates. This research highlights the potential of knowledge-based AI systems to strengthen primary healthcare delivery in developing regions, offering a cost-effective, interpretable, and accessible solution for tropical disease management.