Classifiers based Approach for Pre-Diagnosis of Lung Cancer Disease

Lung cancer disease is one of the dreaded diseases in the developing and developed countries. The pre-diagnosis is an important stage of identifying the target group of persons who can undergo diagnosis stage. Here in this study, prediction of lung cancer is attempted based on symptoms and risk factors. Data collected from the confirmed case of the patients is pre-processed based on multi filter approach. Pre-processed data is then tried with different classifier algorithms. It has been observed that Sequential Minimal Optimization, simple logistic and supervised learning based algorithms resulted in better performance compared to other algorithms. Detailed analysis is done based on Radial Basis function. All these algorithms are