Feature subset selection by genetic algorithms and estimation of distribution algorithms - A case study in the survival of cirrhotic patients treatedwith TIPS

The transjugular intrahepatic portosystemic shunt (TIPS) is an intervention al treatment for cirrhotic patients with portal hypertension. In the light of our medical staff's experience, the consequences of TIPS are not homogen eous for all the patients and a subgroup dies in the first 6 months after T IPS placement. Actually, there is no risk indicator to identify this subgro up of patients before treatment. An investigation for predicting the surviv al of cirrhotic patients treated with TIPS is carried out using a clinical database with 107 cases and 77 attributes. Four supervised machine learning classifiers are applied to discriminate between both subgroups of patients . The application of several feature subset selection (FSS) techniques has significantly improved the predictive accuracy of these classifiers and con siderably reduced the amount of attributes in the classification models. Am ong FSS techniques, FSS-TREE, a new randomized algorithm inspired on the ne w EDA (estimation of distribution algorithm) paradigm has obtained the best average accuracy results for each classifier. (C) 2001 Elsevier Science B. V. All rights reserved.