Multilayered rule-based expert system for diagnosing uveitis

Uveitis is a condition caused by inflammation of the uvea, which is the middle layer of the eye. Uveitis can result in swelling or destruction of the eye tissue, which can lead to visual impairment or blindness [1]. Many diseases, either systemic or localized to the eye, are associated with the symptoms of uveitis. Thus, it is often hard to determine the underlying disease responsible for uveitis, especially when the signs and symptoms are unclear. Additionally, there are few experts on uveitis, especially in poor and developing countries. In this paper, we design and build a rule-based expert system to diagnose uveitis. The main motivation for developing this expert system was to mitigate the lack of human experts by helping general ophthalmologists achieve a correct diagnosis with minimal time and effort. Furthermore, the system can act as a good educational tool for newly graduated doctors, guiding their work with their patients and supporting their diagnostic decisions. The novel multilayer design of the system allows flexibility and ease of scaling to new cases in the future. Many techniques were used to improve the system's diagnostic flexibility and overcome incomplete user input. Tests of the system have yielded promising results.