Subgroup identification-based model selection to improve the predictive performance of individualized dosing
Journal of Pharmacokinetics and Pharmacodynamics · 2024
DOI: 10.1007/s10928-024-09909-8 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Pharmacokinetics and Pharmacodynamics, 2024. Verfasst von Hiie Soeorg und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Microbiology, University of Tartu, Ravila 19, Tartu, 50411, Estonia. hiie.soeorg@ut.ee. Hauptthemen laut MEDLINE: Vancomycin, Anti-Bacterial Agents, Precision Medicine, Models, Biological. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 44 Literaturangaben. Gefördert von: Tartu University Hospital development fund 8090.
Abstract (Originalsprache)
Currently, model-informed precision dosing uses one population pharmacokinetic model that best fits the target population. We aimed to develop a subgroup identification-based model selection approach to improve the predictive performance of individualized dosing, using vancomycin in neonates/infants as a test case. Data from neonates/infants with at least one vancomycin concentration was randomly divided into training and test dataset. Population predictions from published vancomycin population pharmacokinetic models were calculated. The single best-performing model based on various performance metrics, including median absolute percentage error (APE) and percentage of predictions within 20% (P20) or 60% (P60) of measurement, were determined. Clustering based on median APEs or clinical and demographic characteristics and model selection by genetic algorithm was used to group neonates/infants according to their best-performing model. Subsequently, classification trees to predict the best-performing model using clinical and demographic characteristics were developed. A total of 208 vancomycin treatment episodes in training and 88 in test dataset was included. Of 30 identified models from the literature, the single best-performing model for training dataset had P20 26.2-42.6% in test dataset. The best-performing clustering approach based on median APEs or clinical and demographic characteristics and model selection by genetic algorithm had P20 44.1-45.5% in test dataset, whereas P60 was comparable. Our proof-of-concept study shows that the prediction of the best-performing model for each patient according to the proposed model selection approaches has the potential to improve the predictive performance of model-informed precision dosing compared with the single best-performing model approach.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Microbiology, University of Tartu, Ravila 19, Tartu, 50411, Estonia. hiie.soeorg@ut.ee.
- Department of Microbiology, University of Tartu, Ravila 19, Tartu, 50411, Estonia.
- Pediatric Intensive Care Unit, Tartu University Hospital, Puusepa 8, Tartu, 50406, Estonia.
Förderung
- Tartu University Hospital development fund 8090
Zitieren
APA
Soeorg, H., Kalamees, R., Lutsar, I., & Metsvaht, T. (2024). Subgroup identification-based model selection to improve the predictive performance of individualized dosing. Journal of Pharmacokinetics and Pharmacodynamics. https://doi.org/10.1007/s10928-024-09909-8
Vancouver
Soeorg H, Kalamees R, Lutsar I, Metsvaht T. Subgroup identification-based model selection to improve the predictive performance of individualized dosing. Journal of Pharmacokinetics and Pharmacodynamics. 2024. doi:10.1007/s10928-024-09909-8
BibTeX
@article{Soeorg2024,
author = {Soeorg, Hiie and Kalamees, Riste and Lutsar, Irja and Metsvaht, Tuuli},
title = {Subgroup identification-based model selection to improve the predictive performance of individualized dosing},
journal = {Journal of Pharmacokinetics and Pharmacodynamics},
year = {2024},
doi = {10.1007/s10928-024-09909-8}
}
EUVIMED