Urea reduction ratio that considers effects of ultrafiltration and intradialytic urea generation

Partial least squares regression: a valuable method for modeling molecular behavior in hemodialysis

The aim of this work was to use the Partial Least Squares Regression (PLS) technique to fit simple models for the interpretation of an underlying complex process. In this study, the technique was used to build a statistical model for molecular kinetic data obtained from hemodialyzed patients. By using PLS we derived statistical linear models for the prediction of the equilibrated urea concentration which would be reached 30-60 min after the end of the dialysis session. Models with an average relative prediction error (RPE) of less than 0.05% were achieved. The model predictive accuracy was evaluated in a cross-center study yielding an RPE < 3%. The chosen model was robust to variations such as sampling extraction time demonstrating a high capacity for modeling kinetics. It also was found to be useful for bedside monitoring. Finally, the PLS technique allowed identification of the most important co-variables in the model and of those patients with outlier patterns in their molecular dynamics.

Comparison of Standard and Artificial Neural Network Estimators of Hemodialysis Adequacy

The National Kidney Foundation and the European Renal Association recommend routine measurement of hemodialysis (HD) dose and have set standards for adequacy of treatment. We compare the results of five methods for HD dose estimation, classifying each result as adequate or inadequate on the basis of equilibrated (eq) Urea Reduction Ratio (URR(eq)) > or = 65% or Kt/V(eq) > or = 1.2, to assess the accuracy of each method as a diagnostic tool. Data from 113 patients from two different dialysis units were analyzed. Equilibrated postdialysis blood urea was measured 60 min after each hemodialysis session to calculate URR(eq) and Kt/V(eq), considered as gold standard indexes (GSI). URR and Kt/V were estimated by using the Smye formula, an artificial neural network (ANN), modified URR, the second generation Kt/V Daugirdas formula, and standard indexes based on postdialysis urea, then compared to the GSI. For URR, best estimator was ANN (error rate: ER% = 12.70), followed by modified URR (ER% = 17.46%), the Smye (ER% = 22.22), and standard URR (ER% = 23.81). For Kt/V, the Daugirdas equation and the ANN were similar (ER% = 9.52 and 11.11). The single-pool Kt/V (Kt/V(sp)) > or = 1.4 (ERA recommended) produced an ER% = 7.94 and a false positive rate (FPR%) equal to that shown by the ANN (FPR% = 3.17). According to the current threshold limits for HD dose adequacy, the ANN was a reliable and accurate tool for URR monitoring, better than the Smye and the modified URR methods. The use of the ANN urea estimation yields accurate results when used to calculate Kt/V. The Kt/V(sp) with an adequacy threshold of 1.4 is a superior approach for HD adequacy monitoring, suggesting that the current adequacy limits should be reviewed for both URR and Kt/V.

Dialysate-side urea kinetics. Neural network predicts dialysis dose during dialysis

Determination of the adequacy of dialysis is a routine but crucial procedure in patient evaluation. The total dialysis dose, expressed as Kt/V, has been widely recognised to be a major determinant of morbidity and mortality in haemodialysed patients. Many different factors influence the correct determination of Kt/V, such as urea sequestration in different body compartments, access and cardiopulmonary recirculation. These factors are responsible for urea rebound after the end of the haemodialysis session, causing poor Kt/V estimation. There are many techniques that try to overcome this problem. Some of them use analysis of blood-side urea samples, and, in recent years, on-line urea monitors have become available to calculate haemodialysis dose from dialysate-side urea kinetics. All these methods require waiting until the end of the session to calculate the Kt/V dose. In this work, a neural network (NN) method is presented for early prediction of the Kt/V dose. Two different portions of the dialysate urea concentration-time profile (provided by an on-line urea monitor) were analysed: the entire curve A and the first half B, using an NN to predict the Kt/V and compare this with that provided by the monitor. The NN was able to predict Kt/V is the middle of the 4h session (B data) without a significant increase in the percentage error (B data: 6.69% +/- 2.46%; A data: 5.58% +/- 8.77%, mean +/- SD) compared with the monitor Kt/V.

New empiric expressions to calculate single pool Kt/V and equilibriated Kt/V

Most formulae used for Kt/V computations are cumbersome and require variables that are not always available. Even the simplest models involve urea distribution volume or patient postdialysis weight. Calculating urea reduction ratio (URR) is easier and does not require additional variables, but it fails to account for residual renal function or for the removal of urea when urea levels do not change, e.g., during ultrafiltration. The goal of this study was to derive new expressions to calculate Kt/V based on URR using bivariate and multivariate linear and nonlinear models, with the URR adjusted for ultrafiltration volume and time on dialysis. Models were derived from a database of 598 dialysis records with a mean spKt/V of 1.6 (range 0.74-2.8). Models were validated on the same dataset that they were derived from and a separate dataset consisting of 17,190 dialysis records. The validation was made by comparing the empirically derived models with the Gotch and Daugirdas formulae. Among our empirically derived expressions, the closest approximation of the "gold standard," Kt/V, is the multivariate linear model of URR adjusted for ultrafiltration volume. When information about ultrafiltration is not available, the bivariate exponential formula can be successfully used to estimate Kt/V.