Data fusion strategies for performance improvement of a Process Analytical Technology platform consisting of four instruments

An electrospinning case study

Tibor Casian, Attila Farkas, Kinga Ilyés, Balázs Démuth, Enikő Borbás, Lajos Madarász, Zsolt Rapi, Balázs Farkas, Attila Balogh, András Domokos, G. Marosi, Ioan Tomută, Zsombor Kristóf Nagy

Research output: Contribution to journalArticle

Abstract

The aim of this work was to develop a PAT platform consisting of four complementary instruments for the characterization of electrospun amorphous solid dispersions with meloxicam. The investigated methods, namely NIR spectroscopy, Raman spectroscopy, Colorimetry and Image analysis were tested and compared considering the ability to quantify the active pharmaceutical ingredient and to detect production errors reflected in inhomogeneous deposition of fibers. Based on individual performance the calculated RMSEP values ranged between 0.654% and 2.292%. Mid-level data fusion consisting of data compression through latent variables and application of ANN for regression purposes proved efficient, yielding an RMSEP value of 0.153%. Under these conditions the model could be validated accordingly on the full calibration range. The complementarity of the PAT tools, demonstrated from the perspective of captured variability and outlier detection ability, contributed to model performance enhancement through data fusion. To the best of the author's knowledge, this is the first application of data fusion in the field of PAT for efficient handling of big-analytical-data provided by high-throughput instruments.

Original languageEnglish
Article number118473
JournalInternational Journal of Pharmaceutics
Volume567
DOIs
Publication statusPublished - Aug 15 2019

Fingerprint

meloxicam
Data Compression
Colorimetry
Near-Infrared Spectroscopy
Raman Spectrum Analysis
Calibration
Technology
Pharmaceutical Preparations

Keywords

  • Artificial neural networks
  • Data fusion
  • Electrospinning
  • Process Analytical Technology
  • Vibrational spectroscopy

ASJC Scopus subject areas

  • Pharmaceutical Science

Cite this

Data fusion strategies for performance improvement of a Process Analytical Technology platform consisting of four instruments : An electrospinning case study. / Casian, Tibor; Farkas, Attila; Ilyés, Kinga; Démuth, Balázs; Borbás, Enikő; Madarász, Lajos; Rapi, Zsolt; Farkas, Balázs; Balogh, Attila; Domokos, András; Marosi, G.; Tomută, Ioan; Nagy, Zsombor Kristóf.

In: International Journal of Pharmaceutics, Vol. 567, 118473, 15.08.2019.

Research output: Contribution to journalArticle

Casian, Tibor ; Farkas, Attila ; Ilyés, Kinga ; Démuth, Balázs ; Borbás, Enikő ; Madarász, Lajos ; Rapi, Zsolt ; Farkas, Balázs ; Balogh, Attila ; Domokos, András ; Marosi, G. ; Tomută, Ioan ; Nagy, Zsombor Kristóf. / Data fusion strategies for performance improvement of a Process Analytical Technology platform consisting of four instruments : An electrospinning case study. In: International Journal of Pharmaceutics. 2019 ; Vol. 567.
@article{a5aa4e163234473db972279789118cea,
title = "Data fusion strategies for performance improvement of a Process Analytical Technology platform consisting of four instruments: An electrospinning case study",
abstract = "The aim of this work was to develop a PAT platform consisting of four complementary instruments for the characterization of electrospun amorphous solid dispersions with meloxicam. The investigated methods, namely NIR spectroscopy, Raman spectroscopy, Colorimetry and Image analysis were tested and compared considering the ability to quantify the active pharmaceutical ingredient and to detect production errors reflected in inhomogeneous deposition of fibers. Based on individual performance the calculated RMSEP values ranged between 0.654{\%} and 2.292{\%}. Mid-level data fusion consisting of data compression through latent variables and application of ANN for regression purposes proved efficient, yielding an RMSEP value of 0.153{\%}. Under these conditions the model could be validated accordingly on the full calibration range. The complementarity of the PAT tools, demonstrated from the perspective of captured variability and outlier detection ability, contributed to model performance enhancement through data fusion. To the best of the author's knowledge, this is the first application of data fusion in the field of PAT for efficient handling of big-analytical-data provided by high-throughput instruments.",
keywords = "Artificial neural networks, Data fusion, Electrospinning, Process Analytical Technology, Vibrational spectroscopy",
author = "Tibor Casian and Attila Farkas and Kinga Ily{\'e}s and Bal{\'a}zs D{\'e}muth and Enikő Borb{\'a}s and Lajos Madar{\'a}sz and Zsolt Rapi and Bal{\'a}zs Farkas and Attila Balogh and Andr{\'a}s Domokos and G. Marosi and Ioan Tomută and Nagy, {Zsombor Krist{\'o}f}",
year = "2019",
month = "8",
day = "15",
doi = "10.1016/j.ijpharm.2019.118473",
language = "English",
volume = "567",
journal = "International Journal of Pharmaceutics",
issn = "0378-5173",
publisher = "Elsevier",

}

TY - JOUR

T1 - Data fusion strategies for performance improvement of a Process Analytical Technology platform consisting of four instruments

T2 - An electrospinning case study

AU - Casian, Tibor

AU - Farkas, Attila

AU - Ilyés, Kinga

AU - Démuth, Balázs

AU - Borbás, Enikő

AU - Madarász, Lajos

AU - Rapi, Zsolt

AU - Farkas, Balázs

AU - Balogh, Attila

AU - Domokos, András

AU - Marosi, G.

AU - Tomută, Ioan

AU - Nagy, Zsombor Kristóf

PY - 2019/8/15

Y1 - 2019/8/15

N2 - The aim of this work was to develop a PAT platform consisting of four complementary instruments for the characterization of electrospun amorphous solid dispersions with meloxicam. The investigated methods, namely NIR spectroscopy, Raman spectroscopy, Colorimetry and Image analysis were tested and compared considering the ability to quantify the active pharmaceutical ingredient and to detect production errors reflected in inhomogeneous deposition of fibers. Based on individual performance the calculated RMSEP values ranged between 0.654% and 2.292%. Mid-level data fusion consisting of data compression through latent variables and application of ANN for regression purposes proved efficient, yielding an RMSEP value of 0.153%. Under these conditions the model could be validated accordingly on the full calibration range. The complementarity of the PAT tools, demonstrated from the perspective of captured variability and outlier detection ability, contributed to model performance enhancement through data fusion. To the best of the author's knowledge, this is the first application of data fusion in the field of PAT for efficient handling of big-analytical-data provided by high-throughput instruments.

AB - The aim of this work was to develop a PAT platform consisting of four complementary instruments for the characterization of electrospun amorphous solid dispersions with meloxicam. The investigated methods, namely NIR spectroscopy, Raman spectroscopy, Colorimetry and Image analysis were tested and compared considering the ability to quantify the active pharmaceutical ingredient and to detect production errors reflected in inhomogeneous deposition of fibers. Based on individual performance the calculated RMSEP values ranged between 0.654% and 2.292%. Mid-level data fusion consisting of data compression through latent variables and application of ANN for regression purposes proved efficient, yielding an RMSEP value of 0.153%. Under these conditions the model could be validated accordingly on the full calibration range. The complementarity of the PAT tools, demonstrated from the perspective of captured variability and outlier detection ability, contributed to model performance enhancement through data fusion. To the best of the author's knowledge, this is the first application of data fusion in the field of PAT for efficient handling of big-analytical-data provided by high-throughput instruments.

KW - Artificial neural networks

KW - Data fusion

KW - Electrospinning

KW - Process Analytical Technology

KW - Vibrational spectroscopy

UR - http://www.scopus.com/inward/record.url?scp=85067929802&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85067929802&partnerID=8YFLogxK

U2 - 10.1016/j.ijpharm.2019.118473

DO - 10.1016/j.ijpharm.2019.118473

M3 - Article

VL - 567

JO - International Journal of Pharmaceutics

JF - International Journal of Pharmaceutics

SN - 0378-5173

M1 - 118473

ER -