Background. A standardized practical method of postdialysis blood sampling is required to improve the precision of using urea kinetics in the evaluation of haemodialysis dose and to permit comparative audit. The methods recommended in the Renal Association and Dialysis Outcomes Quality Initiative (DOQI) guidelines reduce the blood pump speed to a low rate at the end of haemodialysis before blood sampling after 10 and 15 s respectively. However, these 'low flow' methods compensate only partially for cardiopulmonary recirculation and may be impractical in routine practice because they involve sequential steps and require accurate timing of sampling. Therefore we have evaluated an alternative method of stopping only the dialysate flow at the end of the haemodialysis session before performing post-dialysis blood sampling. Methods. The study was performed in three phases. Serial measurements of blood urea were obtained from arterial and venous samples taken at times 0, 30, 60, 120, 180, 240, 300 and 360 s after stopping dialysate flow and leaving the extracorporeal blood flow rate unchanged at the end of the haemodialysis session in 10 patients, a peripheral venous sample was also taken from the contralateral arm at 0 s to reflect body water urea concentration at the end of dialysis without the effect of access recirculation and with a minimal effect of cardiopulmonary recirculation. The same haemodialysis prescription was repeated in the same 10 patients using the Renal Association method to permit comparison between the two methods. The practical use of the 'stop dialysate flow' method was then evaluated in 117 regular haemodialysis patients undergoing routine monthly assessment of dialysis adequacy and compared with sampling immediately post-dialysis. Results. Within 4 min of stopping the dialysate flow there was no difference between the blood urea concentrations of arterial and venous samples, indicating cessation of diffusion across the dialysis membrane. Also the blood urea concentrations in all of the arterial and venous samples between 4 and 6 min were constant and were equivalent to the blood urea concentration of the peripheral venous sample taken at 0 s. These data suggest that post-dialysis blood sampling may be performed 5 min after stopping dialysate flow at the end of the haemodialysis session. In contrast, the blood urea concentration in the post-dialysis samples obtained using the Renal Association method were lower than the contralateral arm blood urea concentration taken at 0 s (0.31+/-0.42; P<0.05) and consequently the percentage URR was higher (1.35+/-1.84%). In 117 patients the post-dialysis blood urea sample 5 min after stopping dialysate flow averaged 5.49+/-2.11 mmol/l compared with 5.07+/-2.05 mmol/l immediately after the end of the haemodialysis session (P<0.0001). This was equivalent to a reduction in URR from 71.7+/-8.3% with sampling immediately post-dialysis to 69.1+/-9.3% with the 'stop dialysate flow' method. Conclusions. This study shows that there is a window period between 4 and 6 min after stopping dialysate flow at the end of the haemodialysis session when the blood urea concentration in a sample taken from any part of the extracorporeal circuit remains constantly within the co-efficient of variation of laboratory measurement, and is equivalent to a peripheral venous sample taken immediately at the end of the dialysis session. A 'stop dialysate flow' method with blood sampling after 5 min offers several advantages over 'slow flow' methods, since it allows for cardiopulmonary as well as access recirculation, does not require precise timing of blood sampling, and is simple to perform in a busy renal unit. For these reasons the 'stop dialysate flow' method may be used for routine monitoring of the adequacy of delivered haemodialysis and for comparative audit among haemodialysis centres.
