PSO based Rule Optimization for Liver Disease Diagnosis
Abstract
Diagnosing different types of liver diseases clinically is a quite hectic process because patients have to undergo large numbers of independent laboratory tests. On the basis of results and analysis of laboratory test, different liver diseases are classified. Hence to simplify this complex process, a Rule Based Classification Model (RBCM) have developed to predict different types of liver diseases. The proposed model is the combination of decision tree and evolutionary method. Decision trees are employed for identifying valuable information in health databases. The advantage of tree classifiers is to provide rules that are easily interpretable. The C5.0 classification does not require any expert knowledge to select the useful data and can be used with categorical and continuous data. The evolutionary algorithms such as genetic algorithm and particle swarm optimization are used for rule optimization. The proposed algorithm will optimize the rules released from C5.0 classification method with the Particle Swarm Optimization (PSO), to provide the good classification accuracy. It helps doctors in finding the disease symptoms and reduces the diagnosing time and prevents deaths.