Design of a Fuzzy Rule Base Expert System to Predict and Classify the Cardiac Risk to Reduce the Rate of Mortality
The main objective of design of a rule base expert system using fuzzy logic approach is to predict and forecast the risk level of cardiac patients to avoid sudden death. In this proposed system, uncertainty is captured using rule base and classification using fuzzy c-means clustering is discussed to overcome the risk level, so that emergency care can be taken for the cardiac patients with high risk. To predict and classify the cardiac risk based on the controllable risk factors “blood pressure, cholesterol, diabetic, and obesity”, which can be controllable, are taken as inputs for the expert system and the “risk level” of the patient is the output. The input triangular membership functions are Low, Normal, High, and Very High. The output triangular membership functions are Low, Medium, and Very High. The proposed system is used to incorporate the available knowledge into an expert system based on the clinical observations, medical diagnosis, and the expert’s knowledge. The rule base system is validated with the captured data for accuracy and robustness using MATLAB. The results of the experimental analysis in finding significant patterns for heart attack prediction and classification are presented. The implementation of the proposed approach for identifying the cardiac risk level is done with VB.NET.Also, the simulated model using simulink may be generated for the expert system as further enhancement of this work.
Keywords: Cardiac Risk; Risk Factors; Fuzzy Rule Base; Clustering; Simulated Model