Predicting Lung Cancer Stage by Expressions of Protein-Encoding Genes

Abstract

Predicting the stages of cancer accurately is crucial for effective treatmen t planning. In this study, we aimed to develop a model using gene expression d ata and XGBoost (eXtreme Gradient Boosting) that include clinical an d dem ographic variables to predict specific lung cancer stages in patients. B y conducting the feature selection using the Wilcoxon Rank Test, we picked the most impactful genes associated with lung cancer stage prediction. Our model achieved an overall accuracy of 82% in classifying lung cancer stages acco rding to patients’ gene expression data. These findings demonstrate the potential of gene expression analysis and machine learning techniques in improving the accuracy of lung cancer stage prediction, aiding in personalized treatment decisions.