An Empirical Study of Nature-Inspired Algorithms for Feature Selection in Medical Applications

Abstract

Nature-inspired algorithms (NIA) are proven to be the potential tool for solving intricate optimization problems and aid in the development of better computational techniques. In recent years, these algorithms have raised considerable interest to optimize feature selection problems. In literature, NIA is found to select relevant features among available features in the diagnosis of many chronic diseases. In this paper, a comprehensive review of existing nature-inspired feature selection techniques is presented. Along with this, the fundamental definitions of feature selection and the usage of NIA to optimize feature selection are shown. We have given a review showcasing the NIA application for selecting feature subsets from the available features in the domain of medical applications. The paper reviews and analyzes numerous relevant papers from 2008 to 2022 on feature selection through NIA on biomedical applications. Moreover, to find the best optimization algorithm for feature selection, we have conducted experiments among four well-known nature-inspired algorithms on ten benchmark datasets of the biomedical domain for classification. We have reported results on various state-of-the-art evaluation measures and presented the convergence graphs for analysis. Based on the average rank of fitness values, Particle Swarm Optimization is found to be better than Harris Hawk Optimization, Grey Wolf Optimization, and Whale Optimization. In this paper, we have also presented some open challenges of this research area to guide researchers as well as experts of computational intelligence for future work. The paper will help future researchers understand the use and implementation of nature-inspired algorithms for feature selection in the medical domain.