Skip navigation

Please use this identifier to cite or link to this item:
Title: Data-driven modeling of the bicalutamide dissolution from powder systems
Authors: Mendyk, Aleksander
Pacławski, Adam
Szafraniec-Szczęsny, Joanna
Antosik, Agata
Jamróz, Witold
Paluch, Marian
Jachowicz, Renata
Keywords: artificial intelligence; dissolution modeling; multivariate modeling; multi-scale modeling; solubility enhancement
Issue Date: 2020
Citation: AAPS PharmSciTech, 2020, iss. 3, art. no. 111
Abstract: Low solubility of active pharmaceutical compounds (APIs) remains an important challenge in dosage form development process. In the manuscript, empirical models were developed and analyzed in order to predict dissolution of bicalutamide (BCL) from solid dispersion with various carriers. BCL was chosen as an example of a poor watersoluble API. Two separate datasets were created: one from literature data and another based on in-house experimental data. Computational experiments were conducted using artificial intelligence tools based on machine learning (AI/ML) with a plethora of techniques including artificial neural networks, decision trees, rule-based systems, and evolutionary computations. The latter resulting in classical mathematical equations provided models characterized by the lowest prediction error. In-house data turned out to be more homogeneous, as well as formulations were more extensively characterized than literature-based data. Thus, in-house data resulted in better models than literature-based data set. Among the other covariates, the best model uses for prediction of BCL dissolution profile the transmittance from IR spectrum at 1260 cm−1 wavenumber. Ab initio modeling–based in silico simulations were conducted to reveal potential BCL–excipients interaction. All crucial variables were selected automatically by AI/ML tools and resulted in reasonably simple and yet predictive models suitable for application in Quality by Design (QbD) approaches. Presented data-driven model development using AI/ML could be useful in various problems in the field of pharmaceutical technology, resulting in both predictive and investigational tools revealing new knowledge.
DOI: 10.1208/s12249-020-01660-w
ISSN: 1530-9932
Appears in Collections:Artykuły (WNŚiT)

Files in This Item:
File Description SizeFormat 
Mendyk_Article_Data_Driven_Modeling.pdf613,61 kBAdobe PDFView/Open
Show full item record

Uznanie Autorstwa 3.0 Polska Creative Commons License Creative Commons