Application of artificial neural networks for Process Analytical Technology-based dissolution testing

Brigitta Nagy, Dulichár Petra, Dorián László Galata, Balázs Démuth, Enikő Borbás, G. Marosi, Zsombor Kristóf Nagy, Attila Farkas

Research output: Contribution to journalArticle

Abstract

This work proposes the application of artificial neural networks (ANN) to non-destructively predict the in vitro dissolution of pharmaceutical tablets from Process Analytical Technology (PAT) data. An extended release tablet formulation was studied, where the dissolution was influenced by the composition of the tablets and the tableting compression force. NIR and Raman spectra of the intact tablets were measured, and the dissolution of the tablets was modeled directly from the spectral data. Partial Least Square (PLS) regression and ANN models were developed for the different spectroscopic measurements individually as well as by combining them together. ANN provided up to 3% lower root mean square error for prediction (RMSEP) than the PLS models, due to its capability of modeling non-linearity between the process parameters and dissolution curves. The ANN model using reflection NIR spectra provided the most accurate predictions with 6.5 and 63 mean f1 and f2 values between the computed and measured dissolution curves, respectively. Furthermore, ANN served as a straightforward data fusion method without the need for additional preprocessing steps. The method could significantly advance data processing in the PAT environment, contribute to an enhanced real-time release testing procedure and hence the increased efficacy of dissolution testing.

Original languageEnglish
Article number118464
JournalInternational Journal of Pharmaceutics
Volume567
DOIs
Publication statusPublished - Aug 15 2019

Fingerprint

Tablets
Technology
Neural Networks (Computer)
Least-Squares Analysis
Pharmaceutical Preparations

Keywords

  • Artificial neural network
  • Dissolution prediction
  • NIR spectroscopy
  • Process Analytical Technology
  • Raman spectroscopy
  • Real-time release testing

ASJC Scopus subject areas

  • Pharmaceutical Science

Cite this

Application of artificial neural networks for Process Analytical Technology-based dissolution testing. / Nagy, Brigitta; Petra, Dulichár; Galata, Dorián László; Démuth, Balázs; Borbás, Enikő; Marosi, G.; Nagy, Zsombor Kristóf; Farkas, Attila.

In: International Journal of Pharmaceutics, Vol. 567, 118464, 15.08.2019.

Research output: Contribution to journalArticle

Nagy, Brigitta ; Petra, Dulichár ; Galata, Dorián László ; Démuth, Balázs ; Borbás, Enikő ; Marosi, G. ; Nagy, Zsombor Kristóf ; Farkas, Attila. / Application of artificial neural networks for Process Analytical Technology-based dissolution testing. In: International Journal of Pharmaceutics. 2019 ; Vol. 567.
@article{7b1114d4b26e46c1b3cdf791fb4275d7,
title = "Application of artificial neural networks for Process Analytical Technology-based dissolution testing",
abstract = "This work proposes the application of artificial neural networks (ANN) to non-destructively predict the in vitro dissolution of pharmaceutical tablets from Process Analytical Technology (PAT) data. An extended release tablet formulation was studied, where the dissolution was influenced by the composition of the tablets and the tableting compression force. NIR and Raman spectra of the intact tablets were measured, and the dissolution of the tablets was modeled directly from the spectral data. Partial Least Square (PLS) regression and ANN models were developed for the different spectroscopic measurements individually as well as by combining them together. ANN provided up to 3{\%} lower root mean square error for prediction (RMSEP) than the PLS models, due to its capability of modeling non-linearity between the process parameters and dissolution curves. The ANN model using reflection NIR spectra provided the most accurate predictions with 6.5 and 63 mean f1 and f2 values between the computed and measured dissolution curves, respectively. Furthermore, ANN served as a straightforward data fusion method without the need for additional preprocessing steps. The method could significantly advance data processing in the PAT environment, contribute to an enhanced real-time release testing procedure and hence the increased efficacy of dissolution testing.",
keywords = "Artificial neural network, Dissolution prediction, NIR spectroscopy, Process Analytical Technology, Raman spectroscopy, Real-time release testing",
author = "Brigitta Nagy and Dulich{\'a}r Petra and Galata, {Dori{\'a}n L{\'a}szl{\'o}} and Bal{\'a}zs D{\'e}muth and Enikő Borb{\'a}s and G. Marosi and Nagy, {Zsombor Krist{\'o}f} and Attila Farkas",
year = "2019",
month = "8",
day = "15",
doi = "10.1016/j.ijpharm.2019.118464",
language = "English",
volume = "567",
journal = "International Journal of Pharmaceutics",
issn = "0378-5173",
publisher = "Elsevier",

}

TY - JOUR

T1 - Application of artificial neural networks for Process Analytical Technology-based dissolution testing

AU - Nagy, Brigitta

AU - Petra, Dulichár

AU - Galata, Dorián László

AU - Démuth, Balázs

AU - Borbás, Enikő

AU - Marosi, G.

AU - Nagy, Zsombor Kristóf

AU - Farkas, Attila

PY - 2019/8/15

Y1 - 2019/8/15

N2 - This work proposes the application of artificial neural networks (ANN) to non-destructively predict the in vitro dissolution of pharmaceutical tablets from Process Analytical Technology (PAT) data. An extended release tablet formulation was studied, where the dissolution was influenced by the composition of the tablets and the tableting compression force. NIR and Raman spectra of the intact tablets were measured, and the dissolution of the tablets was modeled directly from the spectral data. Partial Least Square (PLS) regression and ANN models were developed for the different spectroscopic measurements individually as well as by combining them together. ANN provided up to 3% lower root mean square error for prediction (RMSEP) than the PLS models, due to its capability of modeling non-linearity between the process parameters and dissolution curves. The ANN model using reflection NIR spectra provided the most accurate predictions with 6.5 and 63 mean f1 and f2 values between the computed and measured dissolution curves, respectively. Furthermore, ANN served as a straightforward data fusion method without the need for additional preprocessing steps. The method could significantly advance data processing in the PAT environment, contribute to an enhanced real-time release testing procedure and hence the increased efficacy of dissolution testing.

AB - This work proposes the application of artificial neural networks (ANN) to non-destructively predict the in vitro dissolution of pharmaceutical tablets from Process Analytical Technology (PAT) data. An extended release tablet formulation was studied, where the dissolution was influenced by the composition of the tablets and the tableting compression force. NIR and Raman spectra of the intact tablets were measured, and the dissolution of the tablets was modeled directly from the spectral data. Partial Least Square (PLS) regression and ANN models were developed for the different spectroscopic measurements individually as well as by combining them together. ANN provided up to 3% lower root mean square error for prediction (RMSEP) than the PLS models, due to its capability of modeling non-linearity between the process parameters and dissolution curves. The ANN model using reflection NIR spectra provided the most accurate predictions with 6.5 and 63 mean f1 and f2 values between the computed and measured dissolution curves, respectively. Furthermore, ANN served as a straightforward data fusion method without the need for additional preprocessing steps. The method could significantly advance data processing in the PAT environment, contribute to an enhanced real-time release testing procedure and hence the increased efficacy of dissolution testing.

KW - Artificial neural network

KW - Dissolution prediction

KW - NIR spectroscopy

KW - Process Analytical Technology

KW - Raman spectroscopy

KW - Real-time release testing

UR - http://www.scopus.com/inward/record.url?scp=85067914824&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85067914824&partnerID=8YFLogxK

U2 - 10.1016/j.ijpharm.2019.118464

DO - 10.1016/j.ijpharm.2019.118464

M3 - Article

VL - 567

JO - International Journal of Pharmaceutics

JF - International Journal of Pharmaceutics

SN - 0378-5173

M1 - 118464

ER -