Machine learning driven bioequivalence risk assessment at an early stage of generic drug development
European Journal of Pharmaceutics and Biopharmaceutics · 2024
DOI: 10.1016/j.ejpb.2024.114553 ↗Kurz gefasst
Fachartikel in der Zeitschrift European Journal of Pharmaceutics and Biopharmaceutics, 2024. Verfasst von Dejan Krajcar und 2 weiteren Autor:innen. Beteiligte Einrichtung: Lek Pharmaceuticals d.d., A Sandoz Company, Verovskova 57, 1526 Ljubljana, Slovenia; Faculty of Pharmacy, University of Ljubljana, Aškerčeva cesta 7,…. Hauptthemen laut MEDLINE: Therapeutic Equivalency, Machine Learning, Drugs, Generic, Drug Development. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Slovenian Research and Innovation Agency.
Abstract (Originalsprache)
BACKGROUND: Bioequivalence risk assessment as an extension of quality risk management lacks examples of quantitative approaches to risk assessment at an early stage of generic drug development. The aim of our study was to develop a model-based approach for bioequivalence risk assessment that uses pharmacokinetic and physicochemical characteristics of drugs as predictors and would standardize the first step of risk assessment. METHODS: The Sandoz in-house bioequivalence database of 128 bioequivalence studies with poorly soluble drugs (23.5% non-bioequivalent) was used to train and validate the model. Four different modeling approaches, random forest, XGBoost, logistic regression and naïve Bayes, were compared. RESULTS: Among the best performing machine learning models, random forest was selected and optimized for the number of features, resulting in an accuracy of 84% on the test data set. The most important features for prediction were those related to solubility (dose number, acid dissociation constant), absorption and elimination rate, effective permeability, variability of pharmacokinetic endpoints, and absolute bioavailability. All features had a conceivable influence on the model predictions. CONCLUSION: The model was used to develop a bioequivalence risk assessment approach to categorize drugs in early development into high, medium or low risk classes.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Lek Pharmaceuticals d.d., A Sandoz Company, Verovskova 57, 1526 Ljubljana, Slovenia; Faculty of Pharmacy, University of Ljubljana, Aškerčeva cesta 7, 1000 Ljubljana, Slovenia. Electronic address: dejan.krajcar@sandoz.co…
- Lek Pharmaceuticals d.d., A Sandoz Company, Verovskova 57, 1526 Ljubljana, Slovenia.
- Faculty of Pharmacy, University of Ljubljana, Aškerčeva cesta 7, 1000 Ljubljana, Slovenia.
Förderung
- Slovenian Research and Innovation Agency
Zitieren
APA
Krajcar, D., Velušček, D., & Grabnar, I. (2024). Machine learning driven bioequivalence risk assessment at an early stage of generic drug development. European Journal of Pharmaceutics and Biopharmaceutics. https://doi.org/10.1016/j.ejpb.2024.114553
Vancouver
Krajcar D, Velušček D, Grabnar I. Machine learning driven bioequivalence risk assessment at an early stage of generic drug development. European Journal of Pharmaceutics and Biopharmaceutics. 2024. doi:10.1016/j.ejpb.2024.114553
BibTeX
@article{Krajcar2024,
author = {Krajcar, Dejan and Velušček, Dejan and Grabnar, Iztok},
title = {Machine learning driven bioequivalence risk assessment at an early stage of generic drug development},
journal = {European Journal of Pharmaceutics and Biopharmaceutics},
year = {2024},
doi = {10.1016/j.ejpb.2024.114553}
}
EUVIMED