EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Low‐dimensional neural ordinary differential equations accounting for inter‐individual variability implemented in Monolix and NONMEM

Dominic Stefan Bräm iD, Bernhard Steiert iD, Marc Pfister iD, Britta Steffens iD, Gilbert Koch iD

CPT: Pharmacometrics & Systems Pharmacology · 2025

DOI: 10.1002/psp4.13265 ↗

Kurz gefasst

Fachartikel in der Zeitschrift CPT: Pharmacometrics & Systems Pharmacology, 2025. Verfasst von Dominic Stefan Bräm und 4 weiteren Autor:innen. Beteiligte Einrichtung: Pediatric Pharmacology and Pharmacometrics, University Children's Hospital Basel (UKBB), University of Basel, Basel, Switzerland. Hauptthemen laut MEDLINE: Software, Neural Networks, Computer, Machine Learning. Die Arbeit wurde bisher 14-mal zitiert (Crossref) und nennt 17 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Neural ordinary differential equations (NODEs) are an emerging machine learning (ML) method to model pharmacometric (PMX) data. Combining mechanism‐based components to describe “known parts” and neural networks to learn “unknown parts” is a promising ML‐based PMX approach. In this work, the implementation of low‐dimensional NODEs in two widely applied PMX software packages (Monolix and NONMEM) is explained. Inter‐individual variability is introduced to NODEs and proposals for the practical implementation of NODEs in such software are presented. The potential of such implementations is shown on various demonstrational datasets available in the Monolix model library, including pharmacokinetic (PK), pharmacodynamic (PD), target‐mediated drug disposition (TMDD), and survival analyses. All datasets were fitted with NODEs in Monolix and NONMEM and showed comparable results to classical modeling approaches. Model codes for demonstrated PK, PKPD, TMDD applications are made available, allowing a reproducible and straight‐forward implementation of NODEs in available PMX software packages.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

SoftwareNeural Networks, ComputerMachine LearningHumansModels, BiologicalPharmacokinetics

Autor:innen und Institutionen

  • Pediatric Pharmacology and Pharmacometrics, University Children's Hospital Basel (UKBB), University of Basel, Basel, Switzerland.
  • Roche Pharma Research and Early Development, Pharmaceutical Sciences, Roche Innovation Center Basel, F. Hoffmann-La Roche Ltd., Basel, Switzerland.

ORCID-Profile: Dominic Stefan Bräm, Bernhard Steiert, Marc Pfister, Britta Steffens, Gilbert Koch

Zitieren

APA

Bräm, D. S., Steiert, B., Pfister, M., Steffens, B., & Koch, G. (2025). Low‐dimensional neural ordinary differential equations accounting for inter‐individual variability implemented in Monolix and NONMEM. CPT: Pharmacometrics & Systems Pharmacology. https://doi.org/10.1002/psp4.13265

Vancouver

Bräm DS, Steiert B, Pfister M, Steffens B, Koch G. Low‐dimensional neural ordinary differential equations accounting for inter‐individual variability implemented in Monolix and NONMEM. CPT: Pharmacometrics & Systems Pharmacology. 2025. doi:10.1002/psp4.13265

BibTeX
@article{Brm2025,
  author = {Bräm, Dominic Stefan and Steiert, Bernhard and Pfister, Marc and Steffens, Britta and Koch, Gilbert},
  title = {Low‐dimensional neural ordinary differential equations accounting for inter‐individual variability implemented in Monolix and NONMEM},
  journal = {CPT: Pharmacometrics & Systems Pharmacology},
  year = {2025},
  doi = {10.1002/psp4.13265}
}
Kostenlos starten →