Early Detection of Lung Cancer Using Machine Learning Techniques

Lung cancer is among the most common and severe diseases in the world. It affects people of all ages, from children to the elderly. Current clinical techniques like X-Ray or other imaging procedures require complicated hardware and high costs. Therefore, the most important concern is the accuracy of the prediction and the use of a reliable method. This increases the need for an efficient and cost-effective machine learning models for medical diagnosis based on medical data sets. Most cases of lung cancer are caused by long-term tobacco smoking. About 10-15% of lung cancer cases occur in non-smokers and 80% of cancer patients is due to smoking. There are many techniques and tools available today for data analysis and data calculation. These technological advances can be used to create prediction models to predict the early stage of lung cancer in a patient. In this study, different classification models are compared such as Random Forest, Naïve Bayes, K-Star, and J48. This involves comparing the performance of the various models. Inevitably, parameters such as precision, recall and accuracy are taken into account to determine which algorithm has the most predictive accuracy.