Supervised Learning Processing Techniques for Pre-Diagnosis of Lung Cancer Disease

Abstract

Lung cancer disease is one of the dreaded disease is leading cause of death among men in developed and developing countries. Its cure rate and prognosis depends mainly on the early detection and diagnosis of the disease. Creating awareness among the general public about the disease and screening probable impact group requires lot of painstaking effort. This paper mainly focuses on selectively screening susceptible people for pre-diagnosis of Lung cancer disease. The approach adopted here is, conceptualizing artificial neural network model, based on statistical parameters based on cancer registry, symptoms and Risk factors. Supervisory delta learning approach is used to train the model. The model is developed using multi layer perceptron network and trained by established Lung cancer data. This model is then used for the test data. Tested data is again compared with the clinical diagnosed report and the model is reconfigured by including the current information and new training weights are computed.