A survey on mining techniques for early lung cancer diagnoses

With the huge growth in the volume of data today, there is an enhanced need to extract meaningful information from the data. Data mining contributes towards this and finds its application across various diverse domains such as in information technology, retail, stock markets, banking, and healthcare among others. The increase in population coupled with the growth in diseases has necessitated the inclusion of data mining in medical diagnosis to extract the underlying pattern. Of these, cancer is one of the widespread diseases that claim over 7 million lives every year and lung cancer accounts for 18% of these mortalities. Earlier researches and case studies indicate that the survival rate of the patients suffering from cancer is higher when the disease is diagnosed at an early stage.Lung cancer, a disease highly dependent on historical data for early diagnosis, has influenced researchers to pursue the data mining techniques for the pre-diagnosis process. The five year survival rate increases to 70% with the early detection at stage 1, when the tumor has not yet spread. Existing medical techniques like X-Ray, Computed Tomography (CT) scan, sputum cytology analysis and other imaging techniques not only require complex equipment and high cost but is also proven to be efficient only in stage 4, when the tumor has metastasized to other parts of the body. The proposed system involves the development of a data mining tool that will help in the classification of patients into the category that could potentially test positive for lung cancer in stage 1. Based on the pre-diagnosis results from the tool, the doctor can perform the diagnosis for the confirmation of tumor in the patient and initiate the treatment at an early stage thereby increasing the survival rate.