ENHANCED LUNG CANCER PREDICTION USING INTEGRATIVE RANDOM FOREST AND XGBOOST APPROACHES
S.AGNES JOSHY
, N.SOUNTHARIYAA
Early Prediction, Lung Cancer, Random Forest ,XG Boost, Machine Learning Models.
Lung cancer remains one of the leading causes of mortality worldwide, making early and accurate detection critical for improving patient outcomes. This study focuses on developing an enhanced lung cancer prediction model using machine learning techniques. We evaluated 10 machine learning algorithms, including Logistic Regression, Decision Tree, K-Nearest Neighbour, Naive Bayes, Support Vector Classifier, Random Forest, XG Boost, Multi-layer Perceptron, and Gradient Boosting, implemented through the Scikit-learn library in Python. To ensure a robust evaluation, stratified K-Fold cross-validation was employed for all models. Following the evaluation, Random Forest and XG Boost emerged as the top-performing models based on their high accuracy, precision, and F1-scores. These models were optimized using grid search hyperparameter tuning, and a voting classifier was constructed to combine their predictions, significantly improving the overall prediction performance. The final model achieved an accuracy of 98.33%, outperforming individual models. Feature engineering played a critical role, with highly correlated variables such as ANXIETY and YELLOW_FINGERS being combined into a new feature to enhance prediction accuracy. The model was tested with new patient data, demonstrating its practical utility in predicting lung cancer risk based on clinical attributes. These results underscore the potential of integrating machine learning models, particularly Random Forest and XG Boost, to create more reliable and accurate lung cancer prediction tools. Future enhancements could involve incorporating medical image processing techniques, such as analyzing CT scans, to further improve the model's ability to detect early signs of lung cancer and broaden its applicability in clinical settings.
"ENHANCED LUNG CANCER PREDICTION USING INTEGRATIVE RANDOM FOREST AND XGBOOST APPROACHES", IJNRD - INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT (www.IJNRD.org), ISSN:2456-4184, Vol.9, Issue 10, page no.c337-c349, October-2024, Available :https://ijnrd.org/papers/IJNRD2410245.pdf
Volume 9
Issue 10,
October-2024
Pages : c337-c349
Paper Reg. ID: IJNRD_301476
Published Paper Id: IJNRD2410245
Downloads: 00020
Research Area: Science and Technology
Country: TIRUNELVELI, TAMILNADU, India
ISSN: 2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar | ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Publisher: IJNRD (IJ Publication) Janvi Wave
