Boosting Lung Cancer Prediction Accuracy Through Advanced Data Processing and Machine Learning Models

This work proposes a complicated voting ensemble model for exact feature selection using AdaBoost, Catboost, XGBoost, and LARF (LASSO and Recursive Feature Elimination). This approach seeks early detection of lung cancer. Sophisticated machine learning in the model increases prediction accuracy above previous techniques. With its 94.81 % accuracy, precision, recall, and fl-scores for both “NO” and “YES” events, the ensemble approach becomes beneficial in spotting positive and negative lung cancer patients. LARF improved feature selection by giving predictive qualities top priority, hence improving model interpretability and performance at once. This model has practical applications as its speed and accuracy exceed past criteria. The results imply that the employment of numerous sophisticated algorithms to handle complicated medical data may help early and accurate detection of lung cancer be facilitated. Investigating how well the model fits in many clinical settings and how to use it with bigger patient datasets will help to validate and enhance its effectiveness.