A model based toolkit for building medical diagnostic support systems in developing countries

One of the most appealing potential applications for artificial intelligence in developing countries is the construction of medical expert systems for use in areas where medical expertise is unavailable or thin on the ground. What is needed is a tool that provides knowledge structuring facilities that can be used by local experts in developing countries and does not require them to become knowledge engineers. This tool is for them, to build and maintain medical diagnostic support systems easily which are locally appropriate in both form and content. The author describes a knowledge acquisition system for medical diagnosis which uses a model-based approach. The system is in the form of a toolkit which is used to construct medical diagnostic support systems with appropriate domain and task knowledge. The toolkit has two main elements; a tool for building a task model and a tool for structuring and fleshing out a domain model. The emphasis is on providing the local expert with facilities which will enable them to enter their knowledge in a familiar form, rather than forcing them to learn a new and alien methodology