A Multi Model Approach for Lung Cancer Classification Using TOPSIS based Feature Selection

Lung cancer remains one of the most prevalent and fatal diseases globally, making early and accurate diagnosis essential for effective treatment. This study integrates advanced feature selection techniques—namely Pearson’s correlation, Information Gain, and Minimum Redundancy Maximum Relevance (mRMR)—alongside the TOPSIS ranking method to identify the most significant features for lung cancer classification. A range of machine learning algorithms, including Logistic Regression, Decision Tree, Support Vector Machine (SVM), Random Forest, K-Nearest Neighbors (KNN), AdaBoost, XGBoost, and Artificial Neural Networks (ANN), are evaluated. Model performance is assessed using accuracy, recall, precision, and F1-score. Experimental results indicate that XGBoost delivers the highest classification accuracy of 95.08%, while KNN demonstrates superior recall at 90.00%, confirming their effectiveness in supporting early lung cancer detection.