A Multifaceted Approach to Lung Cancer Diagnosis Using Machine Learning Techniques

This research investigates the application of machine learning techniques for lung cancer prediction. A comprehensive dataset encompassing patient features and risk variables is analyzed to identify significant factors influencing lung cancer prognosis. Multivariate analysis techniques, including pair plots, violin plots, and scatter plots, are employed to explore the complex relationships between variables and their impact on lung cancer development. Three machine learning algorithms-support vector machine (SVM), decision tree, and K-nearest neighbors (KNN)-are evaluated for their predictive power using confusion matrices and ROC curves. Principal component analysis (PCA) is utilized to reduce the dimensionality of the dataset and improve model performance. The study addresses the limitations of existing lung cancer diagnosis systems, focusing on improving early detection accuracy. By leveraging advanced machine learning algorithms, this research aims to contribute to the development of more effective and accurate lung cancer prediction models.