Abstract
Lung cancer is one of the leading causes of death worldwide. Increasing patient survival rates requires early detection. Traditional methods of diagnosis often result in late-stage detection, necessitating the development of more advanced and accurate predictive models. This paper has proposed a methodology for lung cancer prediction using machine learning models. Synthetic minority over-sampling technique (SMOTE) is used before classification to resolve the problem of class imbalance. Bayesian optimization is used to enhance model’s performance. Performance of three classifiers adaptive boosting (AdaBoost), random forest (RF), and extreme gradient boosting (XGBoost) is evaluated both with and without hyperparmater optimization. Optimized models of RF, AdaBoost and XGBoost achieved accuracies of 96.11%, 95.74% and 95.92% respectively. Results demonstrate the effectiveness of combining machine learning classifiers, SMOTE, and hyperparameter tuning in improving prediction accuracy.