PK/PD-integrated Bayesian platform design for phase II dose regimen optimization

Abstract

Early-phase dose-finding methods increasingly assess toxicity and efficacy jointly, but comparisons based only on administered dose may inadequately characterize regimens differing in schedule. We developed a Bayesian phase II adaptive platform design for regimen optimization that integrates pharmacokinetic/pharmacodynamic (PK/PD) modelling into toxicity, efficacy, regimen selection and adaptation decisions. The proposed PK/PD-informed Regimen Optimization Platform (PROP) design uses a population PK/PD model to generate patient- and population-level predictions of exposure and biological activity. Acute and cumulative toxicities are analysed using a discrete-time time-to-event model informed by PK exposure. Efficacy is evaluated through Bayesian model averaging of exposure-driven and biomarker-driven time-to-event models. The design supports regimen graduation, discontinuation for futility or safety, and addition of unexplored regimens. Performance was evaluated through simulations motivated by an influenza intensive-care setting. Across six scenarios, PROP generally improved graduation and futility decisions, reduced inappropriate graduation, and supported the addition of promising regimens compared with dose-based alternatives. It also more accurately estimated regimen-specific toxicity and arm-specific efficacy, while the model-averaging framework favored the efficacy model consistent with the data-generating mechanism. Dose-based approaches performed better for safety stopping in some scenarios, despite less accurate characterization of the regimen--toxicity relationship. PK/PD-informed platform designs can improve adaptive regimen selection and knowledge generation when dose alone cannot adequately characterize treatment regimens.

Transfer learning in bayesian optimization for aircraft design
Ali Tfaily, Youssef Diouane, Nathalie Bartoli +1
Structural and Multidisciplinary Optimization30 Sep 2026Peer-reviewedCC BY-NC-SAFull textGeneral mathematics General physicsHAL
Portfolio-Based Constrained Multi-Objective Bayesian Optimization for Materials Design
Sushant Sinha, Christofer Hardcastle, Robert Robinson +4
arXiv17 Sep 2026PreprintarXiv licenceFull textStatistics Condensed matterarXiv
A hybrid approach for steady-state production optimization of a real oil and gas platform: Integrating physics-based models, machine learning techniques, and field monitoring signals
Luca Trevisan, Ahmed Shokry, Marco Montini +2
Computers & Chemical Engineering19 Sep 2026Peer-reviewedLicence not statedFull text8 citedStatisticsHAL
Pre-training of Bayesian Optimization Algorithm through Bayesian Optimization
Satoshi Katayama, Shoyo Hunt, Shintaro Masuda +1
arXiv7 Oct 2026PreprintCC BY 4.0Full textStatisticsarXiv
Energy-aware frugal Bayesian optimization
Gaston Plat, Paul Saves, Nathalie Bartoli +2
arXiv11 Sep 2026PreprintCC BY 4.0Full textOptimisation & control General physicsarXiv

Cite

BibTeX RIS

BibTeX

@misc{vuorinen2026pkpdintegrated,
  title = {{PK/PD-integrated Bayesian platform design for phase II dose regimen optimization}},
  author = {Axel Vuorinen and Antoine Guillon and Emmanuelle Comets and Moreno Ursino},
  howpublished = {arXiv},
  year = {2026},
  month = sep,
  doi = {10.48550/arxiv.2609.30072},
  eprint = {2609.30072},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2609.30072},
  note = {CC BY 4.0},
}

RIS

TY  - UNPB
TI  - PK/PD-integrated Bayesian platform design for phase II dose regimen optimization
AU  - Axel Vuorinen
AU  - Antoine Guillon
AU  - Emmanuelle Comets
AU  - Moreno Ursino
PY  - 2026
DA  - 2026/09/25
PB  - arXiv
DO  - 10.48550/arxiv.2609.30072
UR  - https://arxiv.org/abs/2609.30072
AB  - Early-phase dose-finding methods increasingly assess toxicity and efficacy jointly, but comparisons based only on administered dose may inadequately characterize regimens differing in schedule. We developed a Bayesian phase II adaptive platform design for regimen optimization that integrates pharmacokinetic/pharmacodynamic (PK/PD) modelling into toxicity, efficacy, regimen selection and adaptation decisions. The proposed PK/PD-informed Regimen Optimization Platform (PROP) design uses a population PK/PD model to generate patient- and population-level predictions of exposure and biological activity. Acute and cumulative toxicities are analysed using a discrete-time time-to-event model informed by PK exposure. Efficacy is evaluated through Bayesian model averaging of exposure-driven and biomarker-driven time-to-event models. The design supports regimen graduation, discontinuation for futility or safety, and addition of unexplored regimens. Performance was evaluated through simulations motivated by an influenza intensive-care setting. Across six scenarios, PROP generally improved graduation and futility decisions, reduced inappropriate graduation, and supported the addition of promising regimens compared with dose-based alternatives. It also more accurately estimated regimen-specific toxicity and arm-specific efficacy, while the model-averaging framework favored the efficacy model consistent with the data-generating mechanism. Dose-based approaches performed better for safety stopping in some scenarios, despite less accurate characterization of the regimen--toxicity relationship. PK/PD-informed platform designs can improve adaptive regimen selection and knowledge generation when dose alone cannot adequately characterize treatment regimens.
ER  -

Abstract

Related

Cite