• Basappa Herakal
• Sowmya
• Aneesh
• Lavithesh B K
• Navaneeth B

Lung cancer remains one of the most fatal and complex diseases globally, with early detection and accurate survivability prediction being critical for effective treatment. Traditional diagnostic methods often fall short in recognizing early-stage cancer or forecasting long-term outcomes. This implementation paper evaluates the use of ensemble machine learning techniques to develop a hybrid framework that supports both the pre-diagnosis of lung cancer and the prediction of patient survivability. The approach combines multi-model classification strategies and ensemble learning methods such as AdaBoost, Random Forest, and SMO, applied to both clinical symptom datasets and SEER survivability data. Feature selection and preprocessing steps ensure dimensionality reduction and data integrity. By integrating rule-based and statistical models with ensemble learning, the system enhances diagnostic precision and survivability forecasting. The proposed framework not only improves predictive accuracy but also supports the development of intelligent healthcare systems aimed at early intervention and resource-efficient cancer care.

Ensemble Learning, Survivability Prediction, Classification, AdaBoost, Random Forest, Feature Selection.

"ENSEMBLE BASED LUNG CANCER PREDICTION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 7, page no.161-165, July-2025, Available :http://www.jetir.org/papers/JETIRGX06029.pdf

"ENSEMBLE BASED LUNG CANCER PREDICTION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 7, page no. pp161-165, July-2025, Available at : http://www.jetir.org/papers/JETIRGX06029.pdf