Wavelet feature extraction and bio-inspired feature selection for the prognosis of lung cancer − A statistical framework analysis

•Wavelet feature extraction reduces the dimensionality of lung cancer microarray data.•Cuckoo Search and Dragonfly feature selection algorithms preserve relevant gene data.•Versatile classifiers based on probability, distribution, tree, and nonlinear kernels.•Our framework reported better results than the conventional machine learning methods. In this paper, we unleash the potential of wavelet-based feature extraction on Microarray gene expression lung cancer datasets that exhibit high-dimensional feature spaces with thousands of genes, posing dimensionality reduction and feature selection challenges. The Biorthogonal 2.2 wavelet, Coiflets 2 wavelet, and Daubechies 6 wavelet extract features, thereby reducing the dimension of the Microarray gene expression datasets. Afterwards, the Dragonfly and Cuckoo Search bio-inspired algorithms choose the relevant features from the dimensionally reduced microarray data. Further, in the classification phase, the following classifiers are used: Nonlinear Regression, Bayesian Linear Discriminant, Softmax Discriminant, Gaussian Mixture Model, Naive Bayesian, Random Forest, Decision Tree, and Support Vector Machine with linear, polynomial, and Radial Basis Function kernels. The Daubechies 6 wavelet feature extraction and Dragonfly feature selection attained the highest accuracy in the range of 97.23, with an F1 score of 98.32, MCC of 0.90, YI of 91.54 and Kappa of 0.90.