APPLICATION OF EXPLAINABLE ARTIFICIAL INTELLIGENCE IN THE IDENTIFICATION OF NON-SMALL CELL LUNG CANCER BIOMARKERS

Abstract

Worldwide, lung cancer is the second most commonly diagnosed cancer. NSCLC is the most common type of lung cancer in the United States, accounting for 85% of all lung cancer diagnoses. The purpose of this study was to find potential diagnostic biomarkers for NSCLC by application of eXplainable Artificial Intelligence (XAI) on XGBoost machine learning (ML) models trained on binary classification datasets comprising the expression data of 60 non-small cell lung cancer tissue samples and 60 normal healthy tissue samples. After successfully incorporating SHAP values into the ML models, 20 significant genes were identified and were found to be associated with the progression of NSCLC. These identified genes may serve as diagnostic and prognostic biomarkers in patients with NSCLC.