A predictive integrated framework based on the radial basis function for the modelling of the flow of pharmaceutical powders

Maen Alshafiee, Wafa' H. AlAlaween, Daniel Markl, Mithushan Soundaranathan, Ammar Almajaan, Karl Walton, Liam Blunt, Kofi Asare-Addo

Research output: Contribution to journalArticle

Abstract

This study presents a modelling framework to predict the flowability of various commonly used pharmaceutical powders and their blends. The flowability models were trained and validated on 86 samples including single components and binary mixtures. Two modelling paradigms based on artificial intelligence (AI) namely, a radial basis function (RBF) and an integrated network were employed to model the flowability represented by the flow function coefficient (FFC) and the bulk density (RHOB). Both approaches were utilized to map the input parameters (i.e. particle size, shape descriptors and material type) to the flow properties. The input parameters of the blends were determined from the particle size, shape and material type properties of the single components. The results clearly indicated that the integrated network outperformed the single RBF network in terms of the predictive performance and the generalization capabilities. For the integrated network, the coefficient of determination of the testing data set (not used for training the model) for FFC was R2=0.93, reflecting an acceptable predictive power of this model. Since the flowability of the blends can be predicted from single component size and shape descriptors, the integrated network can assist formulators in selecting excipients and their blend concentrations to improve flowability with minimal experimental effort and material resulting in the (i) minimization of the time required, (ii) exploration and examination of the design space, and (iii) minimization of material waste.

LanguageEnglish
Article number118542
Number of pages11
JournalInternational Journal of Pharmaceutics
Volume568
Early online date19 Jul 2019
DOIs
Publication statusPublished - 10 Sep 2019

Fingerprint

Particle Size
Powders
Excipients
Artificial Intelligence
Pharmaceutical Preparations
Datasets

Cite this

@article{786319731b2e47ae8893189f9731b09a,
title = "A predictive integrated framework based on the radial basis function for the modelling of the flow of pharmaceutical powders",
abstract = "This study presents a modelling framework to predict the flowability of various commonly used pharmaceutical powders and their blends. The flowability models were trained and validated on 86 samples including single components and binary mixtures. Two modelling paradigms based on artificial intelligence (AI) namely, a radial basis function (RBF) and an integrated network were employed to model the flowability represented by the flow function coefficient (FFC) and the bulk density (RHOB). Both approaches were utilized to map the input parameters (i.e. particle size, shape descriptors and material type) to the flow properties. The input parameters of the blends were determined from the particle size, shape and material type properties of the single components. The results clearly indicated that the integrated network outperformed the single RBF network in terms of the predictive performance and the generalization capabilities. For the integrated network, the coefficient of determination of the testing data set (not used for training the model) for FFC was R2=0.93, reflecting an acceptable predictive power of this model. Since the flowability of the blends can be predicted from single component size and shape descriptors, the integrated network can assist formulators in selecting excipients and their blend concentrations to improve flowability with minimal experimental effort and material resulting in the (i) minimization of the time required, (ii) exploration and examination of the design space, and (iii) minimization of material waste.",
keywords = "Integrated network, Pharmaceutical powder, Powder flow, Radial basis function",
author = "Maen Alshafiee and AlAlaween, {Wafa' H.} and Daniel Markl and Mithushan Soundaranathan and Ammar Almajaan and Karl Walton and Liam Blunt and Kofi Asare-Addo",
year = "2019",
month = "9",
day = "10",
doi = "10.1016/j.ijpharm.2019.118542",
language = "English",
volume = "568",
journal = "International Journal of Pharmaceutics",
issn = "0378-5173",
publisher = "Elsevier",

}

A predictive integrated framework based on the radial basis function for the modelling of the flow of pharmaceutical powders. / Alshafiee, Maen; AlAlaween, Wafa' H.; Markl, Daniel; Soundaranathan, Mithushan; Almajaan, Ammar; Walton, Karl; Blunt, Liam; Asare-Addo, Kofi.

In: International Journal of Pharmaceutics, Vol. 568, 118542, 10.09.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A predictive integrated framework based on the radial basis function for the modelling of the flow of pharmaceutical powders

AU - Alshafiee, Maen

AU - AlAlaween, Wafa' H.

AU - Markl, Daniel

AU - Soundaranathan, Mithushan

AU - Almajaan, Ammar

AU - Walton, Karl

AU - Blunt, Liam

AU - Asare-Addo, Kofi

PY - 2019/9/10

Y1 - 2019/9/10

N2 - This study presents a modelling framework to predict the flowability of various commonly used pharmaceutical powders and their blends. The flowability models were trained and validated on 86 samples including single components and binary mixtures. Two modelling paradigms based on artificial intelligence (AI) namely, a radial basis function (RBF) and an integrated network were employed to model the flowability represented by the flow function coefficient (FFC) and the bulk density (RHOB). Both approaches were utilized to map the input parameters (i.e. particle size, shape descriptors and material type) to the flow properties. The input parameters of the blends were determined from the particle size, shape and material type properties of the single components. The results clearly indicated that the integrated network outperformed the single RBF network in terms of the predictive performance and the generalization capabilities. For the integrated network, the coefficient of determination of the testing data set (not used for training the model) for FFC was R2=0.93, reflecting an acceptable predictive power of this model. Since the flowability of the blends can be predicted from single component size and shape descriptors, the integrated network can assist formulators in selecting excipients and their blend concentrations to improve flowability with minimal experimental effort and material resulting in the (i) minimization of the time required, (ii) exploration and examination of the design space, and (iii) minimization of material waste.

AB - This study presents a modelling framework to predict the flowability of various commonly used pharmaceutical powders and their blends. The flowability models were trained and validated on 86 samples including single components and binary mixtures. Two modelling paradigms based on artificial intelligence (AI) namely, a radial basis function (RBF) and an integrated network were employed to model the flowability represented by the flow function coefficient (FFC) and the bulk density (RHOB). Both approaches were utilized to map the input parameters (i.e. particle size, shape descriptors and material type) to the flow properties. The input parameters of the blends were determined from the particle size, shape and material type properties of the single components. The results clearly indicated that the integrated network outperformed the single RBF network in terms of the predictive performance and the generalization capabilities. For the integrated network, the coefficient of determination of the testing data set (not used for training the model) for FFC was R2=0.93, reflecting an acceptable predictive power of this model. Since the flowability of the blends can be predicted from single component size and shape descriptors, the integrated network can assist formulators in selecting excipients and their blend concentrations to improve flowability with minimal experimental effort and material resulting in the (i) minimization of the time required, (ii) exploration and examination of the design space, and (iii) minimization of material waste.

KW - Integrated network

KW - Pharmaceutical powder

KW - Powder flow

KW - Radial basis function

UR - http://www.scopus.com/inward/record.url?scp=85069700554&partnerID=8YFLogxK

U2 - 10.1016/j.ijpharm.2019.118542

DO - 10.1016/j.ijpharm.2019.118542

M3 - Article

VL - 568

JO - International Journal of Pharmaceutics

T2 - International Journal of Pharmaceutics

JF - International Journal of Pharmaceutics

SN - 0378-5173

M1 - 118542

ER -