<![CDATA[Lung cancer is the leading cause of cancer-related deaths worldwide, often detected at advanced stages. This study aims to develop an accurate and efficient lung cancer risk prediction system by comparing the performance of four machine learning algorithms: Random Forest, Support Vector Machine (SVM), XGBoost, and Logistic Regression. To address the class imbalance problem in the dataset, this study implements the Synthetic Minority Over-sampling Technique (SMOTE). The dataset used comes from Kaggle and consists of 5000 patient records with 29 predictive features. The research process includes data collection, pre-processing, data splitting, application of SMOTE, data scaling, model definition, model training, model evaluation, and performance comparison of the models. The results of the study show that the Logistic Regression and SVM models demonstrate the best performance with accuracies of 97.20% and 97.40%, respectively, and ROC-AUC scores of 99.80% and 99.66%, respectively. The implementation of the model in a web-based system allows both the general public and health professionals to use the model for predicting lung cancer risk based on identified factors. These results contribute to the development of a lung cancer risk prediction model that can assist in making better medical decisions.]]>
Copyrights © 2026
