A Novel Hybrid Classifier Model for Leukemia Prediction Using Machine Learning Techniques

Abstract

Cancer is known as the second crucial disease that causes the highest cause of mortality across the world. Earlier and accurate cancer prediction with the automated design of a clinical decision support system helps the physicians control the mortality risk and therapeutic intervention. Machine Learning (ML) based prediction approaches are used to identify the appropriate values for cancer prediction. Also, optimization is an essential factor to endeavour proper decision making. A novel convolutional non-influencing feature rejection (CNI-FR) classifier model is utilized to enhance the classifiers' prediction accuracy. In the case of gene analysis, all the features are not highly solicited, and ML provides various approaches for feature selection and classification. It is dependent on the provided input data and its feature distribution. Thus, both feature analysis and classification are required for efficient classification. The primary research objective is to optimize the learning parameters like rejection rate for appropriate cancer prediction of conventional parameters. Here, feature analysis is performed, and the rejection threshold is set for these feature analysis to examine the cancer prediction robustly. Here, various online available cancer dataset is taken, and the proposed classifier model is executed. The outcomes reveal the performance of the anticipated model with other ML classifiers. The predictions based on the proposed model specify that the ML algorithm with its dependencies is suitable for appropriate cancer prediction.