LUNG CANCER RELAPSE PREDICTION USING PARALLEL XGBOOST

Lung cancer has been the most popular form of for decades. Surgery will offer non-small cell lung (NSCLC) patients best hope a cure if is diagnosed in early stage. However, many eventually die their disease due to relapse after surgery. Because no symptoms its stage, researchers try improve methods predict early. This study proposed method more accurately. three stages; feature selection, parallel extreme gradient boost (XGBoost) classifications with different hyperparameters, and selection It used two datasets gene expression microarray types clinical information. The accuracy model excellent compared other machine learning.