Decision Support System For Lung Cancer By using Bayesian Classification

Abstract

In many application domains, classification of complex measurements is essential in a diagnostic process. Correct classification of measurements may in fact be the most critical part of the diagnostic process. The main feature of the proposed system is to provide a sample and integrated tool for designing diagnostic application. Lung cancer is the second most common malignancy in men and the third most common cancer in women. Usually lung cancer nodules have a multifocal origin and a rather poor prognosis. Therefore, a careful review of the symptoms presented and a detailed physical exam greatly help with the diagnosis occurs. This paper proposes a decision support system for lung cancer classification using Bayesian Analysis to help the physician or the patient who tests herself at home for lung cancer with the most possible result. Bayesian classification is one of the classification methods successfully applied to the cancer diagnostic problems. The system stores the knowledge of the medical experts and the medical records of the previous cases. Based on the knowledge stored, the system will learn the patterns using Bayesian Analysis and decide the probability based on the symptoms of the patients. Classifier accuracy is also estimated to get the better decision support system with the minimum error rate by using Bayesian Analysis that provides a theoretical justification and lower error rate than other classifiers, [6].