Model-based approach for two-stage group sequential or adaptive designs in bioequivalence studies using parallel and crossover designs
Statistical Methods in Medical Research · 2025
DOI: 10.1177/09622802251354925 ↗Kurz gefasst
Fachartikel in der Zeitschrift Statistical Methods in Medical Research, 2025. Verfasst von Florence Loingeville und 11 weiteren Autor:innen. Beteiligte Einrichtung: ULR 2694 - METRICS : Evaluation of Health Technologies and Medical Practices, University of Lille, CHU Lille, Lille, France. Hauptthemen laut MEDLINE: Models, Statistical, Research Design. Die Arbeit nennt 36 Literaturangaben. Gefördert von: Center for Drug Evaluation and Research.
Abstract (Originalsprache)
In pharmacokinetic (PK) bioequivalence (BE) analysis, the recommended approach is the two one-sided tests (TOSTs) on non-compartmental analysis (NCA) estimates of area under the plasma drug concentration versus time curve and C m a x (NCA-TOST). Sample size estimation for a BE study requires assumptions on between/within subject variability (B/WSV). When little prior information is available, interim analysis using two-stage group sequential (GS) or adaptive designs (ADs) may be beneficial. GS fixes the second stage size, while AD requires sample re-estimation based on first-stage results. Recent research has proposed model-based (MB) TOST, using nonlinear mixed effects models, as an alternative to NCA-TOST. This work extends GS and AD approaches to MB-TOST. We evaluated these approaches on simulated parallel and two-way crossover designs for a one-compartment PK model, considering three variability levels for initial sample size calculation. We compared final sample size, type I error, and power estimates from one-stage, GS, and AD designs using NCA-TOST and MB-TOST. Results showed both NCA-TOST and MB-TOST reasonably controlled type I error while maintaining adequate power in two-stage GS and AD approaches, based on our limited computation power. Two-stage designs reduced sample size compared to traditional designs, especially for highly variable drugs, with many trials stopping at Stage 1 in AD designs. Our findings suggest MB-TOST may serve as a viable alternative to NCA-TOST for BE assessment in two-stage designs, especially when B/WSV impacts BE results.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- ULR 2694 - METRICS : Evaluation of Health Technologies and Medical Practices, University of Lille, CHU Lille, Lille, France.
- Biostatistics team, Bordeaux Population Health, INSERM U1219, Bordeaux, France.
- Inserm, IAME, Université Paris Cité, Paris, France.
- Division of Quantitative Methods and Modeling, Office of Research and Standards, Office of Generic Drugs, Center for Drug Evaluation and Research, U.S. Food and Drug Administration, Silver Spring, MD USA.
- Office of Biostatistics, Office of Translational Sciences, Center for Drug Evaluation and Research, U.S. Food and Drug Administration, Silver Spring, MD, USA.
ORCID-Profile: Florence Loingeville
Förderung
- Center for Drug Evaluation and Research
Zitieren
APA
Loingeville, F., Rakez, M., Thuy Nguyen, T., Donnelly, M., Fang, L., Feng, K., Zhao, L., Grosser, S., Sun, G., Sun, W., Mentré, F., & Bertrand, J. (2025). Model-based approach for two-stage group sequential or adaptive designs in bioequivalence studies using parallel and crossover designs. Statistical Methods in Medical Research. https://doi.org/10.1177/09622802251354925
Vancouver
Loingeville F, Rakez M, Thuy Nguyen T, Donnelly M, Fang L, Feng K, et al. Model-based approach for two-stage group sequential or adaptive designs in bioequivalence studies using parallel and crossover designs. Statistical Methods in Medical Research. 2025. doi:10.1177/09622802251354925
BibTeX
@article{Loingeville2025,
author = {Loingeville, Florence and Rakez, Manel and Thuy Nguyen, Thu and Donnelly, Mark and Fang, Lanyan and Feng, Kevin and Zhao, Liang and Grosser, Stella and Sun, Guoying and Sun, Wanjie and Mentré, France and Bertrand, Julie},
title = {Model-based approach for two-stage group sequential or adaptive designs in bioequivalence studies using parallel and crossover designs},
journal = {Statistical Methods in Medical Research},
year = {2025},
doi = {10.1177/09622802251354925}
}
EUVIMED