EUVIMEDEUVIMED entdecken
Crossref

Vector‐Based Comparison and Average Slope Can Refine Bioequivalence Claims: A Machine and Deep Learning Approach

Maria Kokkali, Vangelis D Karalis iD

Biopharmaceutics & Drug Disposition · 2026

DOI: 10.1002/bdd.70023 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Biopharmaceutics & Drug Disposition, 2026. Verfasst von Maria Kokkali und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Pharmacy, School of Health Sciences, National and Kapodistrian University of Athens, Athens, Greece. Hauptthemen laut MEDLINE: Deep Learning, Machine Learning, Pharmacokinetics. Die Arbeit nennt 28 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study explored the advantages of two innovative concepts: AS and VBC. AS is a pharmacokinetic parameter that measures absorption rates, whereas VBC analyzes clinical endpoints as vectors, breaking them into independent components. Together, these methods aim to improve the accuracy and efficiency of bioequivalence (BE) studies. The performance of AS and VBC was assessed using 14 actual datasets. The study applied both standard statistical methods required by regulatory authorities and advanced techniques, including machine learning and artificial neural networks. The findings showed that combining AS and VBC accurately measures absorption rates while reducing variability. This approach enhances statistical power, addresses multiplicity issues, and supports smaller sample sizes. These improvements simplify BE studies, lower costs, and shorten completion times. The joint use of AS and VBC provides a precise and efficient method for defining absorption rates in BE studies. These methods improve study outcomes while reducing the resources and time required, making them valuable tools for modern BE analysis.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningMachine LearningPharmacokineticsTherapeutic EquivalencyHumans

Stichwörter der Autor:innen

average slopebioequivalencemachine learningvariabilityvector based comparison

Autor:innen und Institutionen

  • Department of Pharmacy, School of Health Sciences, National and Kapodistrian University of Athens, Athens, Greece.
  • Institute of Applied and Computational Mathematics, Foundation for Research and Technology Hellas (FORTH), Heraklion, Greece.

ORCID-Profile: Vangelis D Karalis

Zitieren

APA

Kokkali, M., & Karalis, V. D. (2026). Vector‐Based Comparison and Average Slope Can Refine Bioequivalence Claims: A Machine and Deep Learning Approach. Biopharmaceutics & Drug Disposition. https://doi.org/10.1002/bdd.70023

Vancouver

Kokkali M, Karalis VD. Vector‐Based Comparison and Average Slope Can Refine Bioequivalence Claims: A Machine and Deep Learning Approach. Biopharmaceutics & Drug Disposition. 2026. doi:10.1002/bdd.70023

BibTeX
@article{Kokkali2026,
  author = {Kokkali, Maria and Karalis, Vangelis D},
  title = {Vector‐Based Comparison and Average Slope Can Refine Bioequivalence Claims: A Machine and Deep Learning Approach},
  journal = {Biopharmaceutics & Drug Disposition},
  year = {2026},
  doi = {10.1002/bdd.70023}
}
Kostenlos starten →