EUVIMEDEUVIMED entdecken
Multizentrische StudieOpen Access · CC BY-NC 4.0

Machine Learning‐Based Model Selection and Averaging Outperform Single‐Model Approaches for a Priori Vancomycin Precision Dosing

Wisse van Os iD, Amaury O'Jeanson iD, Carla Troisi iD, Chun Liu iD, Jordan T Brooks iD, Jasmine H Hughes iD, Dominic M H Tong iD, Ron J Keizer iD

CPT: Pharmacometrics & Systems Pharmacology · 2025

DOI: 10.1002/psp4.70084 ↗

Kurz gefasst

Multizentrische Studie in der Zeitschrift CPT: Pharmacometrics & Systems Pharmacology, 2025. Verfasst von Wisse van Os und 7 weiteren Autor:innen. Beteiligte Einrichtung: Division of Systems Pharmacology & Pharmacy, Leiden Academic Centre for Drug Research, Leiden University, Leiden, the Netherlands. Hauptthemen laut MEDLINE: Machine Learning, Models, Biological, Vancomycin, Drug Dosage Calculations. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: European Union's H2020 Marie Skłodowska-Curie Actions Research and Innovation Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Selecting an appropriate population pharmacokinetic (PK) model for individual patients in model‐informed precision dosing (MIPD) can be challenging, particularly in the absence of therapeutic drug monitoring (TDM) samples. We developed a machine learning (ML) model to guide individualized PK model selection for a priori MIPD of vancomycin based on routinely recorded patient characteristics. This retrospective analysis included 343,636 vancomycin TDM records, each from a distinct adult patient across 156 healthcare centers, along with a priori predictions from six PK models. A multi‐label classification approach was applied, labeling PK model predictions based on whether they fell within 80%–125% of observed TDM values. Various modeling strategies were evaluated using XGBoost as the base algorithm, with binary relevance selected for the final model. At the prediction stage, PK models were ranked and averaged for each patient based on ML‐predicted probabilities that predictions would fall within 80%–125% of the observed concentration. Selecting the highest ranked PK model for each patient and ML‐based model averaging outperformed all single PK models, body mass index‐based selection, and naive averaging. On a population level, these ML approaches resulted in more accurate predictions, a higher proportion of predictions within 80%–125% of observed vancomycin concentrations, and no systematic bias. Predictive performance declined with lower ML‐assigned rankings, and selecting the lowest‐ranked PK model for each patient resulted in worse performance than the worst‐performing single PK model. By guiding the selection of appropriate models and avoiding less suitable ones, ML approaches for a priori MIPD may improve early dosing decisions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningModels, BiologicalVancomycinDrug Dosage CalculationsHumansAnti-Bacterial AgentsRetrospective StudiesBoosting Machine Learning AlgorithmsMaleFemaleYoung AdultAdultMiddle AgedAgedAged, 80 and over

Stichwörter der Autor:innen

XGBoostmachine learningmodel‐informed precision dosing (MIPD)multi‐label classificationpopulation pharmacokineticstherapeutic drug monitoring (TDM)vancomycin

Substanzen

VancomycinAnti-Bacterial Agents

Autor:innen und Institutionen

  • Division of Systems Pharmacology & Pharmacy, Leiden Academic Centre for Drug Research, Leiden University, Leiden, the Netherlands.
  • Department of Clinical Pharmacology, Medical University of Vienna, Vienna, Austria.
  • Department of Pharmacy, Uppsala University, Uppsala, Sweden.
  • Department of Medical and Surgical Sciences, Alma Mater Studiorum-University of Bologna, Bologna, Italy.
  • InsightRX, San Francisco, California, USA.

ORCID-Profile: Wisse van Os, Amaury O'Jeanson, Carla Troisi, Chun Liu, Jordan T Brooks, Jasmine H Hughes, Dominic M H Tong, Ron J Keizer

Förderung

  • European Union's H2020 Marie Skłodowska-Curie Actions Research and Innovation Program

Zitieren

APA

van Os, W., O'Jeanson, A., Troisi, C., Liu, C., Brooks, J. T., Hughes, J. H., Tong, D. M. H., & Keizer, R. J. (2025). Machine Learning‐Based Model Selection and Averaging Outperform Single‐Model Approaches for a Priori Vancomycin Precision Dosing. CPT: Pharmacometrics & Systems Pharmacology. https://doi.org/10.1002/psp4.70084

Vancouver

van Os W, O'Jeanson A, Troisi C, Liu C, Brooks JT, Hughes JH, et al. Machine Learning‐Based Model Selection and Averaging Outperform Single‐Model Approaches for a Priori Vancomycin Precision Dosing. CPT: Pharmacometrics & Systems Pharmacology. 2025. doi:10.1002/psp4.70084

BibTeX
@article{vanOs2025,
  author = {van Os, Wisse and O'Jeanson, Amaury and Troisi, Carla and Liu, Chun and Brooks, Jordan T and Hughes, Jasmine H and Tong, Dominic M H and Keizer, Ron J},
  title = {Machine Learning‐Based Model Selection and Averaging Outperform Single‐Model Approaches for a Priori Vancomycin Precision Dosing},
  journal = {CPT: Pharmacometrics & Systems Pharmacology},
  year = {2025},
  doi = {10.1002/psp4.70084}
}
Kostenlos starten →