A methodological review of data mining techniques in predictive medicine: An application in hemodynamic prediction for abdominal aortic aneurysm disease

Abstract

Modern clinics and hospitals need accurate real-time prediction tools. This paper reviews the importance and present trends of data mining methodologies in predictive medicine by focusing on hemodynamic predictions in abdominal aortic aneurysm (AAA). It also provides potential data mining working frameworks for hemodynamic predictions in AAA. These frameworks either allow the coupling between a typical computational modeling simulation and various data mining techniques, using the existing medical datasets of real-patient and mining it directly using various data mining techniques or implementing visual data mining approach to already available computed results of various hemodynamic features within the AAA models. These approaches allow the possibility of statistically predicting rupture potentials of aneurismal patients and ideally provide an alternate solution for substituting tedious and time-consuming computational modeling. Prediction trends of patient-specific aneurismal conditions via mining huge volume of medical data can also speed up the decision making process in real life medicine.