DATA MINING BASED ASSISTANT TOOL FOR EVALUATING PATIENTS OF CHRONIC LIVER DISEASES

Abstract

For a number of chronic liver diseases, it has been a challenging issue for physicians to elaborate reliable tools for predicting outcome. Liver Cirrhosis belongs to this group of severe conditions for which survival remains the principal end-point. Over a period of decades, a large number of prognostic models have been developed for cirrhosis in general and for various specific chronic liver diseases in particular. Most scores including Child-Pugh score rely on a limited number of variables, which in light of clinical experience, were• felt to affect prognosis and were put together empirically. In contrast, more recent scores including MELD score are based on a subset of variables, which were shown to be significantly, and independently correlated to the outcome by multivariate analysis. The current prognostic models only provide an imprecise estimate of the prognosis of individual patients because they only explain a smaller part of the observed variation in outcome between the patients. A number of important determinants of the course and outcome may not be available or even identified and their interrelationship may be much more complex than can be described with current model types.