Lung Cancer Prediction Using Classification Tree

Abstract

Lung cancer remains one of the major causes of mortality worldwide. But if treated early and diagnosed at an early stage, there is improved chance of survival. The medical community still remains besieged by the front of predictive modeling. Having access to such vast amounts of data is a double-edged sword. The data retrieval challenge is tackled through data mining, but the big data challenge is not yet conquered. Classification cutting algorithms have been employed in this research to predict lung cancer incidence in patients. These are the most appropriate methods for primary health care units as they allow estimation of lung cancer probability taking age, sex, smoking, dyspnea, wheezing, and chest pain into account. Decision tree modeling technique attempts to forecast medical decisions regarding patient referral based on their previous examination results. Heuristic and probabilistic algorithms are used in this model for the purpose of aiding starting physicians in the making of swift and accurate treatment decisions. Increasingly, initial diagnosis is being triggered by the aid of high-level informative and computation technology. Physicians are supposed to be aided with swift and accurate medical decisions towards patients in need in urgent situations.