Lung Cancer Prediction using Rotation Forest Model with Principal Component Analysis

The global prevalence of the fatal condition known as lung cancer requires developers to create precise early detection predictive models. The study presents a new method which combines the Rotation Forest model with Principal Component Analysis (PCA) for improving predictions of lung cancer. The Rotation Forest model combined with Principal Component Analysis obtained increased efficiency by using PCA to eliminate features that duplicated information. The proposed model delivered higher predictive accuracy and reliability for Elvira Biomedical Dataset and surpassed traditional ensemble methods for this purpose. The combined methodology shows experimental support with successful results that deliver high precision rates and recall rates. This research demonstrates how joining ensemble classifiers with feature selection methods creates improved diagnostic capabilities that generate dependable tools for pulmonary cancer detection by medical workers.