Classifiers in Context: Prediction of Radiological Characteristic Ratings for Lung Nodule Malignancy

In this paper, we are exploring a panel of classifier response to an imbalanced medical data set. In this work we are using LIDC (Lung Image Database Consortium) dataset, which is a very good example for imbalanced data. The main objective of this work is to examine how the response of different categories of classifier is, when subjected to imbalanced dataset. We are considering five categories of classifiers which are grouped as, Instance Based classifier, Rule Based classifiers, Functional Classifier, Decision Tree classifier and Ensemble of Classifiers. The results from our experiments will be evaluated based on performance metrics such as Accuracy, Precision, Recall, F-measure, Area under curve and Kappa statistics.