Bayesian forecasting of serum vancomycin concentrations with non-steady-state sampling strategies

The application of three non-steady-state sampling strategies and the fitting of either three or five pharmacokinetic parameter estimates by a two-compartment Bayesian forecasting program was evaluated retrospectively in 27 adult patients with stable renal function. Sampling strategies included a single midpoint concentration, a set of peak and trough concentrations, and three serial vancomycin concentrations. The most precise and least-bias predictions of steady-state peak vancomycin concentrations were observed by using population-based parameter estimates [mean prediction error (ME) = -0.40 and mean absolute error = 5.77]. The addition of non-steady-state feedback concentration(s) did not provide additional information for predictions of future steady-state peak concentrations. The least-bias prediction of steady-state trough vancomycin concentrations was seen when a single midpoint non-steady-state concentration was used (ME = 0.92 and -0.17 for five and three fitted parameter estimates, respectively). The MEs of serial and peak and trough feedback strategies were similar in magnitude to those obtained using population parameters, but in opposite directions (underprediction vs. overprediction, respectively). The fitting of only three parameters produced results similar to those using five parameters. The results from this study confirm our previous evaluation that non-steady-state concentrations provide very minimal information to Bayesian forecasting of future steady-state concentrations.