Gene Expression Mining for Predicting Survivability of Patients in Earlystages of Lung Cancer

After numerous breakthroughs in medicine, microbiology, and pathology in the past century, lung cancerstill remains as a leading cause of cancer-related death even in the developed countries. Lung canceraccounts roughly for 30% of all cancer-related deaths in the world. Diagnosis and treatments are stillbased on traditional histopathology. It is of paramount importance to predict the survivability of patientsin early stages of lung cancer so that specific treatments can be sought. Nonetheless, histopathology hasbeen shown by previous studies to be inadequate in predicting lung cancer development and clinicaloutcome. The microarray technology allows researchers to examine the expression of thousands of genessimultaneously. This paper describes a state-of-the-art machine learning based approach called averagedone-dependence estimators with subsumption resolution to tackle the problem of predicting whether apatient in early stages of lung cancer will survive by mining DNA microarray gene expression data. Tolower the computational complexity, we employ an entropy-based gene selection approach to selectrelevant genes that are directly responsible for lung cancer survivability prognosis. The proposed systemhas achieved an average accuracy of 92.31% in predicting lung cancer survivability over 2 independentdatasets. The experimental results provide confirmation that gene expression mining can be used to predictsurvivability of patients in early stages of lung cancer.