Neuro-Fuzzy System for Post-Dialysis Urea Rebound Prediction

Measuring post dialysis urea rebound (PDUR) requires a 30- or 60-minute post-dialysis sampling, which is inconvenient. This paper presents a novel technique for predicting equilibrated urea concentration and post dialysis urea rebound in the form of a Takagi-Sugeno-Kang fuzzy inference system. The advantage of this neuro-fuzzy hybrid approach is that it doesn´t require 30-60-minute post-dialysis urea sample. Adaptive neuro-fuzzy inference system (ANFIS) was constructed to predict equilibrated urea (C_eq) taken at 60 min after the end of the hemodialysis (HD) session in order to predict PDUR. The accuracy of the ANFIS was prospectively compared with other traditional methods for predicting equilibrated urea (C_eq), PDUR and equilibrated dialysis dose (e_qKt/V). The results are highly promising, and a comparative analysis suggests that the proposed modeling approach outperforms artificial neural networks and other traditional urea kinetic models (UKM).