Stochastic Gates for Covariate Selection in Population Pharmacokinetics Modeling
CPT: Pharmacometrics & Systems Pharmacology · 2026
DOI: 10.1002/psp4.70147 ↗Kurz gefasst
Fachartikel in der Zeitschrift CPT: Pharmacometrics & Systems Pharmacology, 2026. Verfasst von Marija Kekic und 10 weiteren Autor:innen. Beteiligte Einrichtung: Predictive AI & Data, Clinical Pharmacology & Safety Sciences, R&D BioPharmaceuticals, AstraZeneca, Barcelona, Spain. Hauptthemen laut MEDLINE: Models, Biological, Neural Networks, Computer, Pharmacokinetics. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 27 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Covariate selection in population pharmacokinetics modeling is essential for understanding interindividual variability in drug response and optimizing dosing. Traditional stepwise covariate modeling is often time‐consuming, compared to the new machine learning alternatives. This study investigates the use of neural networks with stochastic gates for automated covariate selection, aiming to efficiently identify relevant covariates while penalizing excessive covariate inclusion. On various synthetic datasets, the approach demonstrated robustness in detecting important covariates, overcoming challenges such as high correlations, low covariate frequencies, high interindividual variability, and complex covariate dependencies. In real clinical data from a monalizumab study, the method successfully identified covariates that matched those found by experts. However, for tixagevimab/cilgavimab, it identified a superset of covariates, indicating a potential need for further pruning. This machine learning‐based method enhances the covariate preselection process in population pharmacokinetics model development, offering significant time savings and improving efficiency even under challenging scenarios.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Predictive AI & Data, Clinical Pharmacology & Safety Sciences, R&D BioPharmaceuticals, AstraZeneca, Barcelona, Spain.
- Clinical Pharmacology & Quantitative Pharmacology, Clinical Pharmacology & Safety Sciences, R&D BioPharmaceuticals, AstraZeneca, Cambridge, UK.
- Predictive AI & Data, Clinical Pharmacology & Safety Sciences, R&D BioPharmaceuticals, AstraZeneca, Cambridge, UK.
- Clinical Pharmacology & Quantitative Pharmacology, Clinical Pharmacology & Safety Sciences, R&D BioPharmaceuticals, AstraZeneca, Waltham, MA, USA.
- Clinical Pharmacology & Quantitative Pharmacology, Clinical Pharmacology & Safety Sciences, R&D BioPharmaceuticals, AstraZeneca, Barcelona, Spain.
- Clinical Pharmacology & Quantitative Pharmacology, Clinical Pharmacology & Safety Sciences, R&D BioPharmaceuticals, AstraZeneca, Gaithersburg, MD, USA.
ORCID-Profile: Marija Kekic, Oleg Stepanov, Wenjuan Wang, Sam Richardson, Damilola Olabode, Carlos Traynor, Richard Dearden, Diansong Zhou, Weifeng Tang, Andrzej Nowojewski
Zitieren
APA
Kekic, M., Stepanov, O., Wang, W., Richardson, S., Olabode, D., Traynor, C., Dearden, R., Zhou, D., Tang, W., Gibbs, M., & Nowojewski, A. (2026). Stochastic Gates for Covariate Selection in Population Pharmacokinetics Modeling. CPT: Pharmacometrics & Systems Pharmacology. https://doi.org/10.1002/psp4.70147
Vancouver
Kekic M, Stepanov O, Wang W, Richardson S, Olabode D, Traynor C, et al. Stochastic Gates for Covariate Selection in Population Pharmacokinetics Modeling. CPT: Pharmacometrics & Systems Pharmacology. 2026. doi:10.1002/psp4.70147
BibTeX
@article{Kekic2026,
author = {Kekic, Marija and Stepanov, Oleg and Wang, Wenjuan and Richardson, Sam and Olabode, Damilola and Traynor, Carlos and Dearden, Richard and Zhou, Diansong and Tang, Weifeng and Gibbs, Megan and Nowojewski, Andrzej},
title = {Stochastic Gates for Covariate Selection in Population Pharmacokinetics Modeling},
journal = {CPT: Pharmacometrics & Systems Pharmacology},
year = {2026},
doi = {10.1002/psp4.70147}
}
EUVIMED