Single stage and multistage classification models for the prediction of liver fibrosis degree in patients with chronic hepatitis C infection.

Predicting significant fibrosis or cirrhosis in patients with hepatitis C virus has persistently preoccupied the research agenda of many specialized research centers. Many studies have been conducted to evaluate the use of readily available laboratory tests to predict significant fibrosis or cirrhosis with the purpose to substantially reduce the number of biopsies performed. Although many of them reported significant predictive values of several serum markers for the diagnosis of cirrhosis, none of these diagnostic techniques was successful in accurately predicting early stages of liver fibrosis. Therefore, in this study a single stage classification model and a multistage stepwise classification model based on Neural Network, Decision Tree, Logistic Regression, and Nearest Neighborhood clustering, have been developed to predict individual's liver fibrosis degree. Results showed that the area under the receiver operator curve (AUROC) values of the multistage model ranged from 0.874 to 0.974 which is a higher range than what is reported in current researches with similar conditions.

Artificial neural network for prediction of equilibrated dialysis dose without intradialytic sample.

Post-dialysis urea rebound (PDUR) is a cause of Kt/V overestimation when it is calculated from pre-dialysis and the immediate post-dialysis blood urea collections. Measuring PDUR requires a 30-or 60-min post-dialysis sampling, which is inconvenient. In this study, a supervised neural network was proposed to predict the equilibrated urea (C eq) at 60 min after the end of hemodialysis (HD). Data of 150 patients from a dialysis unit were analyzed. C eq was measured 60 min after each HD session to calculate PDUR, equilibrated urea reduction rate eq (URR), and ( eq Kt/V). The mean percentage of true urea rebound measured after 60 min of HD session was 19.6 ± 10.7. The mean urea rebound observed from the artificial neural network (ANN) was 18.6 ± 13.9%, while the means were 24.8 ± 14.1% and 21.3 ± 3.49% using Smye and Daugirdas methods, respectively. The ANN model achieved a correlation coefficient of 0.97 (P <0.0001), while the Smye and Daugirdas methods yielded R = 0.81 and 0.93, respectively (P <0.0001); the errors of the Smye method were larger than those of the other methods and resulted in a considerable bias in all cases, while the predictive accuracy for ( eq Kt/V) 60 was equally good by the Daugirdas' formula and the ANN . We conclude that the use of the ANN urea estimation yields accurate results when used to calculate ( eq Kt/V).