The article introduces the Prediction-Corrected Visual Predictive Check (pcVPC) as an improved diagnostic tool for evaluating the performance of nonlinear mixed-effects models in population pharmacokinetic (PK) and pharmacodynamic (PD) studies. Traditional Visual Predictive Checks (VPCs) can be misleading when applied to data with large variability in doses or influential covariates, or when dose adjustments are made adaptively. The pcVPC addresses these issues by normalizing the observed and simulated data based on the typical population prediction for the median independent variable within each bin, thereby reducing the variability caused by variations in independent variables. The authors demonstrate the effectiveness of pcVPCs through simulated and real-world examples, showing that they provide enhanced diagnostic power, especially for random effects models. The pcVPC is also shown to be applicable to data from studies with a priori and/or a posteriori dose adaptations, which traditional VPCs often fail to capture accurately. The article concludes that pcVPCs are a valuable addition to the diagnostic toolbox for PK/PD modelers, facilitating the development of more predictive models and improving model-based decision-making.The article introduces the Prediction-Corrected Visual Predictive Check (pcVPC) as an improved diagnostic tool for evaluating the performance of nonlinear mixed-effects models in population pharmacokinetic (PK) and pharmacodynamic (PD) studies. Traditional Visual Predictive Checks (VPCs) can be misleading when applied to data with large variability in doses or influential covariates, or when dose adjustments are made adaptively. The pcVPC addresses these issues by normalizing the observed and simulated data based on the typical population prediction for the median independent variable within each bin, thereby reducing the variability caused by variations in independent variables. The authors demonstrate the effectiveness of pcVPCs through simulated and real-world examples, showing that they provide enhanced diagnostic power, especially for random effects models. The pcVPC is also shown to be applicable to data from studies with a priori and/or a posteriori dose adaptations, which traditional VPCs often fail to capture accurately. The article concludes that pcVPCs are a valuable addition to the diagnostic toolbox for PK/PD modelers, facilitating the development of more predictive models and improving model-based decision-making.