Model‐informed vancomycin precision dosing by population pharmacokinetics combined with machine learning algorithms
British Journal of Clinical Pharmacology · 2026-09 · 92 (9) · 3169-3179
DOI: 10.1002/bcp.70621 ↗Kurz gefasst
Fachartikel in der Zeitschrift British Journal of Clinical Pharmacology, online erschienen am 20.05.2026. Verfasst von Lei Shi und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pharmacy, The Third Affiliated Hospital of Soochow University/The First People's Hospital of Changzhou, Changzhou, China. Hauptthemen laut MEDLINE: Vancomycin, Anti-Bacterial Agents, Drug Monitoring, Machine Learning. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 18 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Changzhou Science and Technology Program.
Abstract (Originalsprache)
Aims
Achieving the target AUC/MIC remains a critical challenge in vancomycin therapeutic drug monitoring, with traditional empirical dosing regimens often leading to suboptimal outcomes. This study aimed to develop and validate a novel population pharmacokinetic (PopPK)‐informed machine learning model to optimize TDM‐guided dose adjustments. By accurately predicting the 24‐h area under the curve (AUC), the model assists clinicians in rapidly individualizing regimens, thereby improving target attainment, reducing subsequent modifications and minimizing toxicity.
Methods
A total of 1140 vancomycin TDM samples were analysed. Five machine learning models were developed and compared. Model performance assessed using R 2 , RMSE, Lin's concordance correlation coefficient (CCC), mean percentage error (MPE) and mean absolute percentage error (MAPE). The top‐performing model (ANN) was subsequently validated on an independent test set. Its performance, interpretability and clinical safety were further examined using SHAP analysis, Bland–Altman plots, error grid analysis (EGA) and ROC curve evaluation.
Results
The ANN (MLP) model demonstrated the best comprehensive performance. It achieved the highest R 2 (0.920 ± 0.027) and CCC (0.960 ± 0.011), coupled with the lowest RMSE (0.498 ± 0.076 L/h) and minimal systematic bias (MPE: 1.290 ± 1.774). SHAP analysis identified DV (measured concentration), Cys (mg/L) and Last dose as the three most influential predictive features.
Conclusions
The ANN model achieved exceptional accuracy, robustness and clinical safety in predicting individualized vancomycin clearance. This model is deployable as an instantaneous, point‐of‐care CDSS tool, offering a powerful new pathway to solve the long‐standing challenges of accessibility and accuracy in routine TDM practice.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Pharmacy, The Third Affiliated Hospital of Soochow University/The First People's Hospital of Changzhou, Changzhou, China.
Förderung
- Changzhou Science and Technology Program
Zitieren
APA
Shi, L., Hu, N., Ling, J., Yang, X., & Chen, R. (2026). Model‐informed vancomycin precision dosing by population pharmacokinetics combined with machine learning algorithms. British Journal of Clinical Pharmacology, 92(9), 3169-3179. https://doi.org/10.1002/bcp.70621
Vancouver
Shi L, Hu N, Ling J, Yang X, Chen R. Model‐informed vancomycin precision dosing by population pharmacokinetics combined with machine learning algorithms. British Journal of Clinical Pharmacology. 2026;92(9):3169-3179. doi:10.1002/bcp.70621
BibTeX
@article{Shi2026,
author = {Shi, Lei and Hu, Nan and Ling, Jing and Yang, Xuping and Chen, Rong},
title = {Model‐informed vancomycin precision dosing by population pharmacokinetics combined with machine learning algorithms},
journal = {British Journal of Clinical Pharmacology},
year = {2026},
volume = {92},
number = {9},
pages = {3169--3179},
doi = {10.1002/bcp.70621}
}
EUVIMED