Multisite Retrospective Review of Outcomes in Renal Replacement Therapy for Neonates with Inborn Errors of Metabolism

Abstract

Objective: To assess the outcomes of neonates in a contemporary multi-institutional cohort who receive renal replacement therapy (RRT) for hyperammonemia.

Study design: We performed a retrospective analysis of 51 neonatal patients with confirmed inborn errors of metabolism that were treated at 9 different children's hospitals in the US between 2000 and 2015.

Results: Twenty-nine patients received hemodialysis (57%), 21 patients received continuous renal replacement therapy (41%), and 1 patient received peritoneal dialysis (2%). The median age at admission of both survivors (n = 33 [65%]) and nonsurvivors (n = 18) was 3 days. Peak ammonia and ammonia at admission were not significantly different between survivors and nonsurvivors. Hemodialysis, having more than 1 indication for RRT in addition to hyperammonemia, and complications during RRT were all risk factors for mortality. After accounting for multiple patient factors by multivariable analyses, hemodialysis was associated with a higher risk of death compared with continuous renal replacement therapy. When clinical factors including evidence of renal dysfunction, number of complications, concurrent extracorporeal membrane oxygenation, vasopressor requirement, and degree of hyperammonemia were held constant in a single Cox regression model, the hazard ratio for death with hemodialysis was 4.07 (95% CI 0.908-18.2, P value = .067). To help providers caring for neonates with hyperammonemia understand their patient's likelihood of survival, we created a predictive model with input variables known at the start of RRT.

Conclusions: Our large, multicenter retrospective review supports the use of continuous renal replacement therapy for neonatal hyperammonemia.

Keywords: IEM; RRT; ammonia; dialysis; survival.

Figure 1.

Outcomes over time based on peak ammonia level and RRT modality. X-axis plots time in years. Y-axis plots peak ammonia level (μmol/L). Shapes of data points highlight individuals who received CRRT vs hemodialysis as an initial RRT modality (Δ represents those that received hemodialysis and ○ represents CRRT). Shaded shapes denote nonsurvival whereas open shapes represent those that survived.

Figure 2.

Predictive model for nonsurvival. A, Receiver operating characteristic curve, where the x-axis plots the false positive rate (1-specificity) and the y-axis plots the true positive rate (sensitivity) for predicted probability thresholds varying from 0 to 1. The area under this curve (AUC) is a value between 0 and 1 representing the performance of the model. The diagonal line represents the results from a model making random predictions and has an AUC value of 0.5. B, Performance of model prediction for nonsurvival.