Predicting five-year overall survival in patients with non-small cell lung cancer by reliefF algorithm and random forests

Abstract

Non-small Cell Lung Cancer (NSCLC) is a leading death disease in many countries. Many studies are focusing on exact surgical approaches to treat the disease. The five-year overall survival rate for NSCLC patients is typically predicted by traditional regression models with small samples and data size. In this paper, we introduce machine learning tools with feature selection algorithms and random forests classifier to predict the five-year overall survival rate based on a large database. The results of this experiment show that our proposed framework is better than other machine learning approaches to predict the five-year overall survival rate.