Lung Cancer Detection using Machine Learning: A Data-Driven Approach

Lung cancer is very common and most dangerous among all cancers because of its quick progression and late diagnosis. Treatment results and patient survival rates are greatly enhanced by early identification of lung cancer. Conventional diagnostic procedures, such as imaging and biopsy, are frequently costly, time-consuming, and need highly skilled personnel. Machine learning (ML) techniques have made it possible to create automatic and effective diagnostic systems that can help doctors to discover lung cancer early. In recent years, many researchers applied machine learning models in early detection for lung cancer. The objective of this research is to apply several ML models for lung cancer detection with high rate of accuracy. Several supervised machine learning classifiers are applied for lung cancer detection and contrasted in this study. Lung cancer datasets with important clinical parameters like age, smoking history, genetics, and tumor characteristics are used to train these models. The study's objective is to evaluate the accuracy of these models' predictions. Six very popular ML models are selected on the basis of their performance in predicting other diseases. These models are applied for lung cancer detection. It is observed that Logistic Regression performs the best in detecting lung cancer with an accuracy of 98.39%.