Estimation of Ganciclovir Exposure in Adults Transplant Patients by Machine Learning
The AAPS Journal · 2025
DOI: 10.1208/s12248-025-01034-9 ↗Kurz gefasst
Validierungsstudie in der Zeitschrift The AAPS Journal, 2025. Verfasst von Hamza Sayadi und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pharmacology, Toxicology and Pharmacovigilance, CHU de Limoges, Limoges, France. Hauptthemen laut MEDLINE: Machine Learning, Antiviral Agents, Valganciclovir, Ganciclovir. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Université de Limoges.
Abstract (Originalsprache)
Introduction
Valganciclovir, a prodrug of ganciclovir (GCV), is used to prevent cytomegalovirus infection after transplantation, with doses adjusted based on creatinine clearance (CrCL) to target GCV AUC0-24 h of 40–60 mg*h/L. This sometimes leads to overexposure or underexposure. This study aimed to train, test and validate machine learning (ML) algorithms for accurate GCV AUC0-24 h estimation in solid organ transplantation.
Methods
We simulated patients for different dosing regimen (900 mg/24 h, 450 mg/24 h, 450 mg/48 h, 450 mg/72 h) using two literature population pharmacokinetic models, allocating 75% for training and 25% for testing. Simulations from two other literature models and real patients provided validation datasets. Three independent sets of ML algorithms were created for each regimen, incorporating CrCL and 2 or 3 concentrations. We evaluated their performance on testing and validation datasets and compared them with MAP-BE.
Results
XGBoost using 3 concentrations generated the most accurate predictions. In testing dataset, they exhibited a relative bias of -0.02 to 1.5% and a relative RMSE of 2.6 to 8.5%. In the validation dataset, a relative bias of 1.5 to 5.8% and 8.9 to 16.5%, and a relative RMSE of 8.5 to 9.6% and 10.7% to 19.7% were observed depending on the model used. XGBoost algorithms outperformed or matched MAP-BE, showing enhanced generalization and robustness in their estimates. When applied to real patients’ data, algorithms using 2 concentrations showed relative bias of 1.26% and relative RMSE of 12.68%.
Conclusions
XGBoost ML models accurately estimated GCV AUC0-24 h from limited samples and CrCL, providing a strategy for optimized therapeutic drug monitoring. Graphical Abstract
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Pharmacology, Toxicology and Pharmacovigilance, CHU de Limoges, Limoges, France.
- Pharmacology & Transplantation, INSERM U1248, Université de Limoges, 2 Rue du Pr Descottes, F-87000, Limoges, France.
- INERIS, Experimental Toxicology and Modeling Unit (TEAM), Parc ALATA BP2, Verneuil en Halatte, France.
- Service de Maladies Infectieuses et Tropicales, CHU Dupuytren, Limoges, France.
- Department of Pharmacology, Toxicology and Pharmacovigilance, CHU de Limoges, Limoges, France. jean-baptiste.woillard@unilim.fr.
- Pharmacology & Transplantation, INSERM U1248, Université de Limoges, 2 Rue du Pr Descottes, F-87000, Limoges, France. jean-baptiste.woillard@unilim.fr.
ORCID-Profile: Jean-Baptiste Woillard
Förderung
- Université de Limoges
Zitieren
APA
Sayadi, H., Fromage, Y., Labriffe, M., Billat, P. A., Codde, C., Arraki Zava, S., Marquet, P., & Woillard, J. B. (2025). Estimation of Ganciclovir Exposure in Adults Transplant Patients by Machine Learning. The AAPS Journal. https://doi.org/10.1208/s12248-025-01034-9
Vancouver
Sayadi H, Fromage Y, Labriffe M, Billat PA, Codde C, Arraki Zava S, et al. Estimation of Ganciclovir Exposure in Adults Transplant Patients by Machine Learning. The AAPS Journal. 2025. doi:10.1208/s12248-025-01034-9
BibTeX
@article{Sayadi2025,
author = {Sayadi, Hamza and Fromage, Yeleen and Labriffe, Marc and Billat, Pierre-André and Codde, Cyrielle and Arraki Zava, Selim and Marquet, Pierre and Woillard, Jean-Baptiste},
title = {Estimation of Ganciclovir Exposure in Adults Transplant Patients by Machine Learning},
journal = {The AAPS Journal},
year = {2025},
doi = {10.1208/s12248-025-01034-9}
}
EUVIMED