A Survey on Lung Cancer Prediction using ML Algorithms

Cancer which can be defined as a disease in which an abnormal cells divide uncontrollably and destroy body tissue. Lung cancer is the most common killer and plays an important role in mortality of vast amount of people. Lung cancer is the second most common cancer among others. Major reason for lung cancer is due to smoking. To prevent lung cancer deaths, high risk individuals are being screened with low-dose CT scans, because early prediction doubles the survival rate of lung cancer patients. Automatically identifying cancerous lesions in CT scans will save radiologists a lot of time. It will make diagnosing more affordable and hence will save many more lives. Currently lung cancer is predicting by using MRI scan and CT scans. We proposed a new system to predict lung cancer using textual data. In particular, we investigated sex, variables related to smoking history and addiction to nicotine, personal medical history, family history of lung cancer etc. In this work, we use supervised learning algorithms namely logistic regression, k-nearest neighbour etc., to predict lung cancer. Aim of the paper is to propose a model for early prediction and correct diagnosis of the disease which will help the doctor in saving the life of the patient.