Lung cancer is a critical disease that requires early detection through clinical testing in the healthcare system. Although various traditional machine learning (ML) methods are used to analyze lung cancer disease, their performance is not as effective as that of emerging approaches, which require improvement through the use of advanced parameter techniques. Thus, this system proposes a hyperparameter-based machine learning model to test the same dataset, aiming to improve performance according to the evaluation metric parameters. The proposed model is demonstrated using a lung cancer dataset and various hyperparameter approaches through an ML algorithm to enhance overall performance. The experiments were conducted using traditional and hyperparameter-based machine learning (ML) algorithms, and their corresponding performances were analyzed according to individual methods. The performance of each technique, optimized under hyperparameters, is superior to that of traditional methods. According to the evaluation, naïve Bayes performed well (with an accuracy of 91%) in traditional methods, whereas XGBoost performed well (with an accuracy of 96%) in hyperparameter-based methods, compared to all other ML algorithms.