Abstract:
Health insurance is insurance against the risk in occurring medical expenses among individuals .By
estimating the overall risk of health care and health system expenses, among a targeted group, an insurer
develops a routine finance such as monthly premium, to ensure that money is available to pay for the
health care benefits specified in the insurance agreement. A service provider, having a contract with the
insurer, sends medical claim that provides information on patient, the service provider, Treatments,
procedures, and the medical bill for each service. Claim processing is a challenging process that requires
an expert to analyze various claim information and make a decision free of error. It also takes the experts
time and energy to analyze claims individually. Another challenge in medical claim processing is
detecting fraud and burst billing. The aim of this research was to develop a prototype knowledge based
system for medical claim processing. Three experts from Ethiopian health insurance agency were
purposively selected and interviewed, using semi structured interviews, to acquire the domain knowledge
.The knowledge was then represented using rule based representation. SWI-Prolog was used as a tool to
develop the prototype system. The user’s acceptance of the prototype system by visual interaction method
that by showing the prototype system to the domain experts was conducted result is 83.3%. In addition,
performance of the prototype system was evaluated using case testing method. The test result of a
prototype system performance testing using f-Measure is 0.90. The prototype system certainly addresses
the domain area and assists experts in making more precise decisions. However, further study should be
done on integrating natural the system with natural languages and case based reasoning.
