A rule based expert system for syncope prediction

Mining unstructured attributes is renowned technique for predicting the potential causes of diseases. However, it is complex process to develop prediction mechanism for diseases those comprise characteristics like dataset-unavailability and lengthy diagnoses procedures. Syncope is classified as one of such disease. It reduces quality of life of a person which undergoes recurrent episodes. Rule based expert systems obtain information from human experts and create rules using that information. This paper presents a rule based expert system for predicting syncope disease. Association rule mining is applied on syncope data obtained from AFIC & NIHD. Predicate logic technique is used to polish the association rules in order to draw stimulating production rules that could be used with our expert system. The proposed expert system predicts syncope 100% accurately.