A Holistic Performance Comparison for Lung Cancer Classification Using Swarm Intelligence Techniques

Abstract

In the field of bioinformatics, feature selection in classification of cancer is a primary area of research and utilized to select the most informative genes from thousands of genes in the microarray. Microarray data is generally noisy, is highly redundant, and has an extremely asymmetric dimensionality, as the majority of the genes present here are believed to be uninformative. The paper adopts a methodology of classification of high dimensional lung cancer microarray data utilizing feature selection and optimization techniques. The methodology is divided into two stages; firstly, the ranking of each gene is done based on the standard gene selection techniques like Information Gain, Relief–F test, Chi-square statistic, and T-statistic test. As a result, the gathering of top scored genes is assimilated, and a new feature subset is obtained. In the second stage, the new feature subset is further optimized by using swarm intelligence techniques like Grasshopper Optimization (GO), Moth Flame Optimization (MFO), Bacterial Foraging Optimization (BFO), Krill Herd Optimization (KHO), and Artificial Fish Swarm Optimization (AFSO), and finally, an optimized subset is utilized. The selected genes are used for classification, and the classifiers used here are Naïve Bayesian Classifier (NBC), Decision Trees (DT), Support Vector Machines (SVM), and K-Nearest Neighbour (KNN). The best results are shown when Relief-F test is computed with AFSO and classified with Decision Trees classifier for hundred genes, and the highest classification accuracy of 99.10% is obtained.

Microarray Gene Expression Classification: An Efficient Feature Selection Using Hybrid Swarm Intelligence Algorithm

“…This process involves selecting a subset of genes that are most relevant to the classification task, which can improve the performance of the algorithms, reduce data dimensionality, and enhance the results' interpretability [5]. A range of algorithms have been used for multiclass gene expression classification, including (SVM), (ANN), decision trees, and (k-NN), and their performance has been compared in various studies [4]. Metaheuristics, such as genetic algorithms, particle swarm optimization, and artificial bee colonies, have also been utilized for feature selection in microarray gene expression data [6,7].…”

“…Additionally, several studies have employed Swarm Intelligence for multi-class cancer diagnosis using microarray datasets [1] and have shown promising results in terms of accuracy and robustness [3,4] organized a survey based on a comprehensive review to check the feasibilities and possibilities of the SI-based algorithm in terms of feature selection and optimization. Similar conduct is followed by [8] to check the feasibility of hybrid mechanisms of SI-based techniques and their conducted measures.…”

“…It entails the judicious selection of the most relevant genes from the initial microarray data, thereby reducing data dimensionality, enhancing result interpretability, and ultimately improving classification algorithm performance. The importance of this aspect is underscored by comprehensive systematic reviews, exemplified by a study that conducted an extensive analysis of feature selection methods in the context of cancer classification [4]. Multiclass gene expression classification employs a diverse array of classification algorithms, including but not limited to support vector machines (SVM), artificial neural networks (ANN), decision trees, and k-nearest neighbors (k-NN).…”

Lung and colon cancer classification using hybrid principle component analysis network‐extreme learning machine

“…Prabhakar et al 22 used optimization and feature selection strategies to conduct lung classification. This approach was split into two stages: first, each gene was ranked, and a new feature subset was created using common gene selection procedures such as T‐statistic test, Chi‐square statistic, relief–F test, and information gain.…”

Effect of Ropivacaine Combined with Small Doses of Triamcinolone and Continuous Nerve Block of Unilateral Paravertebral Canal Guided by Ultrasound on Metastasis after Radical Treatment of Lung Cancer

“…Thus, selecting the optimum characteristic genes in tumor assessment is crucial. The strategies must be capable of robustly selecting a set with the most informative genes from a large database [ 13 ]. This article examines the categorization of lung disease using selection of features as well as enhancement strategies [ 14 ].…”