Case-based intelligent tutoring systems

Education of medical diagnosis and therapeutic problems are certainly a good task for Case-Based Reasoning (CBR) Intelligent Tutoring Systems (ITS). The purpose of this study is to develop a CBR Intelligent Tutoring System to assist young doctors in the diagnosis of cancer diseases. The system provides recommendations for controlling pain and providing symptom relief in advanced cancer. It can be used as a tool to aid and hopefully improve the quality of care given for those suffering intractable pain. The system is very useful in the management of the problem, and its task to aid young doctors to check their diagnosis. The paper describes the architecture of a prototype namely: Cancer-R that is a hybrid system, which combines rule-based and CBR. Its knowledge base is diverse and linked through a number of indices, frames and relationships. The bulk of this knowledge consists of actual case histories and includes 70 cancered patient cases; some are real Egyptian cases and some from the Internet. The system uses the CBR strategy to record and retrieve its knowledge. The initial diagnostic process is done though firing of rules in the rule-base knowledge. These rules encode information about patients' symptoms and pathological examinations.