What question did this study set out to answer?

This study aims to identify the most accurate pharmacokinetic model for voriconazole in Japanese patients and determine factors influencing prediction errors.

July 11, 2026Open Access

Evaluation of Voriconazole Population Pharmacokinetics in Japanese Patients and Factors Influencing Prediction Accuracy: A Machine Learning Approach

YUYumi UemuraKitasato University Hospital TKToshiaki KomatsuKitasato University Hospital YSYumi SuzukiKitasato University Hospital

Key Points

This study aims to identify the most accurate pharmacokinetic model for voriconazole in Japanese patients and determine factors influencing prediction errors.
Retrospective analysis of 174 adult inpatients receiving voriconazole within 14 days of therapy.
Evaluation of eight population pharmacokinetic models using prediction error metrics.
Classification and regression tree analysis with leave-one-out cross-validation to identify factors affecting prediction accuracy.
Model H, incorporating the albumin-bilirubin score, achieved the best performance with a relative root mean square error of 2.97.
Mean normalized prediction distribution error was 0.774, indicating systematic underprediction.
The best model achieved a training accuracy of 69.5%, while internal validation showed accuracy of 56.9% with an area under the curve of 0.568.

Abstract

Voriconazole (VRCZ) exhibits highly variable pharmacokinetics. Although CYP2C19 poor metabolizers are common in Japan, routine genetic testing is rarely performed in daily clinical practice. Consequently, existing population pharmacokinetic (Pop-PK) models that lack genetic data require external validation in Japanese clinical settings. This study aimed to identify the most accurate nongenetic Pop-PK model for this population and elucidate the factors influencing prediction errors. We retrospectively analyzed 174 adult inpatients who received VRCZ within the first 14 d of therapy. Eight Pop-PK models were evaluated using prediction error metrics and specific clinical criteria. For the best-performing model, normalized prediction distribution error (NPDE) analysis was conducted. Subsequently, a classification and regression tree (CART) analysis with leave-one-out cross-validation (LOOCV) was performed to identify factors associated with prediction accuracy. Model H, incorporating the albumin-bilirubin (ALBI) score, performed best (relative root mean square error 2.97, criteria 33.91%, median prediction error (MDPE) -29.06%). However, NPDE analysis (mean 0.774, variance 2.394) revealed residual systematic underprediction and substantial unmodeled variability. CART analysis identified C-reactive protein (CRP) as the primary determinant of accuracy. While the best model (age, platelet count, serum creatinine, and CRP) achieved a training accuracy of 69.5%, internal validation via LOOCV yielded an accuracy of 56.9% and a multi-class area under the receiver operating characteristic curve of 0.568. While the ALBI-score-based Model H is the most accurate, predictions remain limited in high-inflammation states due to inherent stochastic variability. Stratifying patients by baseline CRP level is crucial for optimizing the initial VRCZ dosing.

KI fragen

Bookmark

View Full Paper