Abstract :

Lung Cancer Continues To Be A Primary Source Of Global Death, Highlighting The Imperative For Early Identification By Advanced Prediction Technologies. This Study Offers A Thorough Methodology For Precise Lung Cancer Prediction Through The Integration Of Sophisticated Feature Engineering, Model Optimization, And Explainable Learning Techniques. The Publicly Accessible Lung Cancer Risk Dataset From Kaggle Is Examined, Preprocessed By Eliminating Duplicates, Applying Label Encoding, And Partitioning The Data. Feature Selection Is Performed Using Recursive Feature Elimination (RFE) Utilizing Support Vector Machine (SVM) To Identify The Most Distinguishing Qualities. A Variety Of Machine Learning Algorithms, Such As Logistic Regression, Gaussian Naïve Bayes, Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), K-Nearest Neighbor (KNN), Decision Tree (DT), Random Forest (RF), And XGBoost, Are Trained And Evaluated Based On Accuracy, Precision, Recall, F1-score, And Matthews Correlation Coefficient. Enhanced Optimization Is Attained Through The Integration Of The Nelder-Mead Algorithm With XGBoost, Resulting In Greater Predictive Capability. Experimental Findings Indicate That The Optimized XGBoost Model Attains 100% Accuracy, Surpassing All Individual Models. A Voting Classifier That Integrates Gradient Boosting, XGBoost, LightGBM, And CatBoost Attains 100% Accuracy, Hence Affirming The Efficacy Of Ensemble Learning Methodologies. Model Interpretability Is Improved By LIME And SHAP, Which Elucidate The Significance Of Essential Aspects, Hence Providing Dependability In Clinical Decision Assistance.

Published:

08-4-2026

Issue:

Vol. 26 No. 4 (2026)

Page Nos:

1707-1719

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite