Development of a tropical disease diagnosis system using artificial neural network and GIS

Expert systems for diagnosis of tropical diseases have been developed and implemented for over a decade with varying degrees of success. While the recent introduction of artificial neural networks has helped to improve the diagnosis accuracy of such systems, this aspect is still negatively affected by the number of supported diseases. A large number of supported diseases usually corresponds to a high number of overlapping symptoms, which results in a considerable drop in diagnosis accuracy. This is particularly important when diagnosing patients returning from holiday or business trips which took them through a number of different tropical regions. The paper presents a system dedicated to diagnosis of patients returning from various tropical countries. The system integrates an artificial neural network with a Geographic Information System (GIS) in order to enhance the diagnostic process. As a result, the system provides several layers of diagnosis support, depending on the types and number of provided patient characteristics. The system has been developed in cooperation with the University Center of Maritime and Tropical Medicine located in the city of Gdynia in northern Poland and applied to diagnosis of patients with malaria, dengue and stechiostomasis with promising results.