Artificial Intelligence-Based Lung Cancer Data Classification

Abstract

The article presents the results of an artificial intelligence-based study on the effectiveness of ensemble learning methods to improve accuracy in a lung cancer dataset. The results demonstrated that the Gradient Boosting, AdaBoost, LGBM, and SGD algorithms achieved the highest performance with an accuracy rate of 95.6%, while also providing strong precision, sensitivity, and F1-scores. Random Forest and XGBoost, with an accuracy of 91.3%, achieved successful results, proving their capacity to correctly distinguish between both classes. Overall, the ensemble methods used in this study exhibited strong performance in terms of both accuracy and generalization.