Predicting quality of life for lung transplant recipients: A hybrid genetic algorithms-based methodology

Feature selection, a critical pre-processing step for data mining, is aimed at determining representative variables/predictors from a large and feature-rich dataset for development of an effective prediction model. The purpose of this paper is to develop a hybrid methodology for feature selection using genetic algorithms to identify such representative features (input variables) and thereby to ensure the development of the best possible analytic model to predict and explain the target variable, quality of life (QoL), for patients undergoing a lung transplant overseen by the United Network for Organ Sharing (UNOS). The evaluation of three classification models, GA-kNN, GA-SVM, and GA-ANN, demonstrated that performance of the lung transplantation process has significantly improved via the GA-SVM approach, although the other two models have also yielded considerably high prediction accuracies. This study is unique in that it proposes a hybrid GA-based feature selection methodology along with design and development of several highly accurate classification algorithms to identify the most important features in the large and feature rich UNOS transplant dataset for lung transplantation.