Optimal Feature Selection Methods for Chronic Kidney Disease Classification using Intelligent Optimization Algorithms

Aim: The classification of medical data gives more importance to identify the existence of the disease. Background: Numerous classification algorithms for chronic kidney disease (CKD) are developed that produce better classification results. But, the inclusion of different factors in the identification of CKD reduces the effectiveness of the employed classification algorithm. Objective: To overcome this issue, feature selection (FS) approaches are proposed to minimize the computational complexity and also to improve the classification performance in the identification of CKD. Since numerous bio-inspired based FS methodologies are developed, a need arises to examine the performance of feature selection approaches of different algorithms on the identification of CKD. Method: This paper proposes a new framework for the classification and prediction of CKD. Three feature selection approaches are used, namely Ant Colony Optimization (ACO) algorithm, Genetic Algorithm (GA), and Particle Swarm Optimization (PSO) in the classification process of CKD. Finally, logistic regression (LR) classifier is employed for effective classification. Results: The effectiveness of the ACO-FS, GA-FS, and PSO-FS are validated by testing it against a benchmark CKD dataset. Conclusion: The empirical results state that the ACO-FS algorithm performs well and the results reported that the classification performance is improved by the inclusion of feature selection methodologies in CKD classification.