Determination of vancomycin pharmacokinetics in neonates to develop practical initial dosing recommendations

Abstract

Variability in neonatal vancomycin pharmacokinetics and the lack of consensus for optimal trough concentrations in neonatal intensive care units pose challenges to dosing vancomycin in neonates. Our objective was to determine vancomycin pharmacokinetics in neonates and evaluate dosing regimens to identify whether practical initial recommendations that targeted trough concentrations most commonly used in neonatal intensive care units could be determined. Fifty neonates who received vancomycin with at least one set of steady-state levels were evaluated retrospectively. Mean pharmacokinetic values were determined using first-order pharmacokinetic equations, and Monte Carlo simulation was used to evaluate initial dosing recommendations for target trough concentrations of 15 to 20 mg/liter, 5 to 20 mg/liter, and ≤20 mg/liter. Monte Carlo simulation revealed that dosing by mg/kg of body weight was optimal where intermittent dosing of 9 to 12 mg/kg intravenously (i.v.) every 8 h (q8h) had the highest probability of attaining a target trough concentration of 15 to 20 mg/liter. However, continuous infusion with a loading dose of 10 mg/kg followed by 25 to 30 mg/kg per day infused over 24 h had the best overall probability of target attainment. Initial intermittent dosing of 9 to 15 mg/kg i.v. q12h was optimal for target trough concentrations of 5 to 20 mg/liter and ≤20 mg/liter. In conclusion, we determined that the practical initial vancomycin dose of 10 mg/kg vancomycin i.v. q12h was optimal for vancomycin trough concentrations of either 5 to 20 mg/liter or ≤20 mg/liter and that the same initial dose q8h was optimal for target trough concentrations of 15 to 20 mg/liter. However, due to large interpatient vancomycin pharmacokinetic variability in neonates, monitoring of serum concentrations is recommended when trough concentrations between 15 and 20 mg/liter or 5 and 20 mg/liter are desired.

FIG 1

Scatterplots of individual patient predicted (based on multiple linear regression model equation) versus observed CL (liter/h) (A) and V (liters) (B).