Towards an Artificial Intelligence Framework for Early Diagnosis and Prediction of Lung Cancer

Abstract

Lung cancer is the 3 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">rd</sup> most common cancer and the 1st cause of cancer death. It is the 2 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">nd</sup> most common tumor in men and 2nd in women, with approximately 32,300 and 16,800 new cases per year, respectively. In this context, the well-integrated of Artificial Intelligence in cancer research could improve early diagnosis and prediction for ensuring better health outcomes. In the present paper, an Artificial Intelligence framework for early diagnosis and prediction of lung cancer is presented, and different evaluation criteria are used in the experiment for estimating and validating the performance of our system. Various possible modeling methods can be used in this research work. In our case, the choice fell on Neural Networks (ANNs), Naive Bayes (NBs), k-nearest neighbors (KNN), Support vector machines (SVMs), Decision Trees (DTs), and Logistic regression (LRs). The experimental results showed that the Support Vector Machines provide a better prediction in terms of effectiveness and efficiency.