A Comparative Study on Data Mining Classifiers to Predict Lung Cancer and Types of NSCLC

Abstract

Lung cancer is one of the most common types of cancer, which is the main cause of death in humans. In order to be cured, cancer must be diagnosed at an early stage. Lung cancer, also known as lung carcinoma, is a malignant tumor that forms in the lungs and is characterized by unchecked cell proliferation. Non-small cell lung cancer (NSCLC) and small cell lung cancer (SCLC) are the two main subtypes of lung cancer. This research examines lung cancer symptoms and risk factors and uses Machine Learning algorithms to identify lung cancer patients from healthy people. These algorithms also distinguish pathological non-small cell lung carcinoma's three types. During pre-diagnosis, this classification helps choose the next step. The optimal data mining strategy is chosen by comparing its results. For the two datasets, SVM and XGBoost methods perform best.