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

A Practical Tutorial on Physics‐Informed Networks for Pharmacometrics and Quantitative Systems Pharmacology

Nazanin Ahmadi Daryakenari iD, Mohammad Kohandel iD

CPT: Pharmacometrics & Systems Pharmacology · 2026

DOI: 10.1002/psp4.70343 ↗

Kurz gefasst

Fachartikel in der Zeitschrift CPT: Pharmacometrics & Systems Pharmacology, 2026. Verfasst von Nazanin Ahmadi Daryakenari und 1 weiteren Autor:innen. Beteiligte Einrichtung: Center for Biomedical Engineering, Brown University, Providence, Rhode Island, USA. Hauptthemen laut MEDLINE: Neural Networks, Computer, Pharmacology. Die Arbeit nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Inverse problems in pharmacometrics and quantitative systems pharmacology (QSP) often involve sparse, noisy data, limited measurable states, and complex dynamical systems. Traditional parameter estimation methods can struggle with ill‐posed problems, stiffness, discontinuities, and gray‐box scenarios where only part of the system dynamics is known or observable. This tutorial provides an end‐to‐end, reproducible workflow for applying physics‐informed neural networks (PINNs) to PK/PD/QSP inverse problems and gray‐box discovery tasks. We present three worked case studies: (1) constant parameter recovery in a three‐state compartmental system, (2) gray‐box discovery of an unknown right‐hand‐side function, and (3) inference of a time‐varying chemotherapy efficacy function under partial observation. For each, we provide implementation guidance, validation checks, and practical advice on collocation design, feature expansion, optimizer selection, numerical precision, constraint enforcement, loss weighting, and residual‐based attention. We also discuss when to consider newer architectures such as Kolmogorov–Arnold networks (KANs) as drop‐in alternatives to standard multilayer perceptrons. All code and notebooks are provided through our PhINs library, short for Pharmacometrics‐Informed Networks, and are publicly available at https://github.com/NazAhmadi/PhINs/ .

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerPharmacologyHumansPharmacokineticsSystems Biology

Stichwörter der Autor:innen

Kolmogorov–Arnold networksgray‐box modelinginverse problemspharmacodynamicspharmacokineticsphysics‐informed neural networksquantitative systems pharmacology

Autor:innen und Institutionen

  • Center for Biomedical Engineering, Brown University, Providence, Rhode Island, USA.
  • Department of Applied Mathematics, University of Waterloo, Waterloo, Ontario, Canada.

ORCID-Profile: Nazanin Ahmadi Daryakenari, Mohammad Kohandel

Zitieren

APA

Ahmadi Daryakenari, N., & Kohandel, M. (2026). A Practical Tutorial on Physics‐Informed Networks for Pharmacometrics and Quantitative Systems Pharmacology. CPT: Pharmacometrics & Systems Pharmacology. https://doi.org/10.1002/psp4.70343

Vancouver

Ahmadi Daryakenari N, Kohandel M. A Practical Tutorial on Physics‐Informed Networks for Pharmacometrics and Quantitative Systems Pharmacology. CPT: Pharmacometrics & Systems Pharmacology. 2026. doi:10.1002/psp4.70343

BibTeX
@article{AhmadiDaryakenari2026,
  author = {Ahmadi Daryakenari, Nazanin and Kohandel, Mohammad},
  title = {A Practical Tutorial on Physics‐Informed Networks for Pharmacometrics and Quantitative Systems Pharmacology},
  journal = {CPT: Pharmacometrics & Systems Pharmacology},
  year = {2026},
  doi = {10.1002/psp4.70343}
}
Kostenlos starten →