Comparison of Various Computational Models for the Accurate Detection of Lung Cancer and Interpreting Using XAI

A thorough comparison of the many computer models created to reliably identify lung cancer is explained via this research paper. Advanced Machine-learning algorithms are implemented to analyze these models in detail in order to find out how well they work at predicting whether a person’s is at the risk of cancer of lungs, based on their symptoms and lifestyle choices. The study uses Explainable Artificial Intelligence (XAI) approaches, namely LIME and SHAP, to understand and explain the logic behind these models’ predictions in order to shed light on their inner workings. The study examines a broad dataset that includes a variety of cases that are at risk for lung cancer and assesses the effectiveness of various models such as S.V.M. (support vector machines), and its various kernels, R.F.(random forests), boosting, and decision trees. By means of rigorous testing and analysis, the study endeavors to ascertain the merits and demerits of every model, furnishing insightful information that might bolster the progression of precise lung cancer detection methods.