Association Between Neural Network And System Dynamics To Predict Dialysis Dose During Hemodialysis

The total dialysis dose, expressed as Kt/V, has been widely recognized to be a major determinant of morbidity and mortality in hemodialyzed 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 hemodialysis session, causing poor Kt/ V estimation. In this work, system dynamics model was combined with a neural network (NN) method for early prediction of the Kt/V dose. Two different portions of the urea concentration-time profile provided by the system dynamics (on-line urea monitor) were analyzed: 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 system dynamics model. 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: 6.65%±2.51%; A data: 5.62%±8.65%) compared with the system dynamics Kt/ V.