Gene Expression Mining for Predicting Survivability of Patients in Early Stages of Lung Cancer

After numerous breakthroughs in medicine, microbiology, and pathology in the past century, lung cancer still remains as a leading cause of cancer-related death even in the developed countries. Lung cancer accounts roughly for 30% of all cancer-related deaths in the world. Diagnosis and treatments are still based on traditional histopathology. It is of paramount importance to predict the survivability of patients in early stages of lung cancer so that specific treatments can be sought. Nonetheless, histopathology has been shown by previous studies to be inadequate in predicting lung cancer development and clinical outcome. The microarray technology allows researchers to examine the expression of thousands of genes simultaneously. This paper describes a state-of-the-art machine learning based approach called averaged one-dependence estimators with subsumption resolution to tackle the problem of predicting whether a patient in early stages of lung cancer will survive by mining DNA microarray gene expression data. To lower the computational complexity, we employ an entropy-based gene selection approach to select relevant genes that are directly responsible for lung cancer survivability prognosis. The proposed system has achieved an average accuracy of 92.31% in predicting lung cancer survivability over 2 independent datasets. The experimental results provide confirmation that gene expression mining can be used to predict survivability of patients in early stages of lung cancer.