Computational Intelligence and Neuroscience

Research Article

An Efficient Cancer Classification Model Using Microarray and High-Dimensional Data

Table 1

Review of previous studies on the feature selection, optimization, and classification methods.


Author	Datasets	Method	Remark

[29] Shukla and Tripathi (2020)	DLBCL	(JMI) Joint mutual information (mRMR) information gain (IG)	This research introduced modern filter-based gene selection technique for detecting biomarkers from microarray data.
[30] Kilicarslan et al. (2020)	Ovarian, leukemia, and Central Nervous system (CNS)	Relief-F of support vector machines (SVM), coevolutionary neural networks (CNN)	This research introduced a hybrid approach based on Relief-F and CNN for cancer diagnosis and classification.
[31] Pashaei et al. (2016)	Colon tumor ALL, AML, 4 (CNS) MLL	Binary black hole algorithm (BBHA) and random forest ranking (RFR)	The authors introduced gene selection and classification techniques to microarray data based on RFR and BBHA.
[32] Pradana and Aditsania	Breast cancer	Binary particle swarm optimization (BPSO) and Decision Tree C4.5	This research introduced binary PSO and DT for cancer detection based on microarray data classification.
[33] Mantovani et al.	UCI	J48 DTs	They presented induction algorithm and introduced hyperparameter tuning of a Decision Tree induction algorithm.
[34] Abbas et al. (2021)	Breast cancer	Whale optimization algorithm (WOA), extremely randomized tree BCD-WERT	This research introduced a novel model for breast cancer detection using WOA optimization based on extremely randomized tree algorithm and efficient features.
[35] Reddy et al.	Srivastava, G. (2020)	UCI heart disease	This research presented an adaptive genetic fuzzy logic algorithm and introduced a hybrid GA and a fuzzy logic classifier for heart diagnosis and disease.
[36] Qaraad et al. (2020)	Colon cancer, breast cancer, prostate cancer	Elastic NET PSO algorithm	This research introduced parameters optimization of Elastic NET using PSO algorithm for high-dimensional data.
[37] El Kafrawy et al. (2020)	De novo acute myeloid leukemia	Recursive feature elimination (RFE), tree-based feature selection (TBFS)	This research introduced multifeature selection with machine learning for de novo acute myeloid leukemia in Egypt.
[38] Turgut et al. (2020)	Breast cancer	AdaBoost and Gradient Boosting random forest, logistic regression	This research introduced classification for microarray breast cancer data using machine learning methods.