Models for prediction of mortality from cirrhosis with special reference to artificial neural network: a critical review

Abstract

Listen

Translate article

Prediction of mortality of patients with cirrhosis of liver, a common and potentially fatal disease, is important for timely listing of patients for liver transplantation. The Child-Pugh scoring system has been widely used for predicting the outcome of liver cirrhosis. The Model for End-Stage Liver Disease (MELD) score has recently become popular for prediction of short-term mortality for organ allocation. A few studies that evaluated artificial neural network (ANN)-based model for prediction of outcome of cirrhosis of liver in terms of mortality have consistently shown it to be superior to Child-Pugh scoring and logistic regression-based models; it is worth noting that MELD score is also derived using the logistic regression model. Due to the inherent ability of neural network-based systems in identifying complex nonlinear interactions, ANN-based models are expected to perform better than most linear models, such as regression-based models. More studies are needed on ANN-based models for prediction of mortality of patients with cirrhosis of liver and its value in prioritization of organ allocation for treatment of patients with cirrhosis of liver.