An Explainable Artificial Intelligence Based Early Lung Cancer Risk Prediction Using LightGBM

Abstract

Lung cancer is the most common cancer in the world and is also the deadliest. Early diagnosis can improve patients' life expectancy and reduce the cost of treatment. The aim of this study is to help physicians and patients by using explainable artificial intelligence methods to early diagnose risk of lung cancer. This study will create an opportunity for physicians to make early diagnosis and treatment strategies for patients. In this study, a machine learning model was developed to predict the risk of lung cancer by using the LightGBM algorithm. Furthermore, the SHAP method is used to explain why and how the model's predictions are made, thus making the AI model reliable. These explanations increase the acceptability and reliability of the predictions made by model, while helping physicians and patients understand the model's decisions. The results obtained show that the developed LightGBM model can predict the risk of lung cancer with a 100% accuracy rate. The model has achieved great results in terms of accuracy rate and sensitivity. In addition, the SHAP analyses explain which features each of the model's predictions is based on, which will increase the confidence of physicians and patients in the decisions of artificial intelligence.