Advancing Medical Practice Through Computer Expert Systems

This research is designed to enable the clinicians to identify certain diseases and describe methods of treatment to be carried out. The Java programming language is the tool for use to design the system. In the system, a number of patient cases are selected as prototypes and stored in a separate database. The knowledge is acquired from literature review and human experts of the specific domain and is used as a base for analysis, diagnosis and treatment recommendations. Different rules exist for diagnosis based on three groups of determining factors of Sr (Sign/Symptom/Investigating report is Strongly Required for Diagnosis), Rn (Sign/Symptom/Investigating report is Relevant but Not necessarily required) and Nr (Sign/Symptom/Investigating report is Not Related/Relevant). The system provides a simple, interactive, graphical user interface. The employment of a low cost software such as Java makes the system affordable to the medical doctors, who are the end users. It is expected that the use of the system will enhance the diagnosis of certain diseases and so reduce the problems that come with mis-diagnosis including their mortality. This in turn reduces healthcare cost and improves the quality and outcomes of healthcare especially in the developing African countries where malaria is endemic and every aspect of health resources manpower, technology, finances, etc.—is in short supply.