FarFaR - Pharmacy Repository
University of Belgrade, Faculty of Pharmacy
    • English
    • Српски
    • Српски (Serbia)
  • English 
    • English
    • Serbian (Cyrillic)
    • Serbian (Latin)
  • Login
View Item 
  •   FarFaR
  • Pharmacy
  • Radovi istraživača / Researchers’ publications
  • View Item
  •   FarFaR
  • Pharmacy
  • Radovi istraživača / Researchers’ publications
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Optimization of matrix tablets controlled drug release using Elman dynamic neural networks and decision trees

Authorized Users Only
2012
Authors
Petrović, Jelena
Ibrić, Svetlana
Betz, Gabriele
Đurić, Zorica
Article (Published version)
Metadata
Show full item record
Abstract
The main objective of the study was to develop artificial intelligence methods for optimization of drug release from matrix tablets regardless of the matrix type. Static and dynamic artificial neural networks of the same topology were developed to model dissolution profiles of different matrix tablets types (hydrophilic/lipid) using formulation composition, compression force used for tableting and tablets porosity and tensile strength as input data. Potential application of decision trees in discovering knowledge from experimental data was also investigated. Polyethylene oxide polymer and glyceryl palmitostearate were used as matrix forming materials for hydrophilic and lipid matrix tablets, respectively whereas selected model drugs were diclofenac sodium and caffeine. Matrix tablets were prepared by direct compression method and tested for in vitro dissolution profiles. Optimization of static and dynamic neural networks used for modeling of drug release was performed using Monte Carlo... simulations or genetic algorithms optimizer. Decision trees were constructed following discretization of data. Calculated difference (f(1)) and similarity (f(2)) factors for predicted and experimentally obtained dissolution profiles of test matrix tablets formulations indicate that Elman dynamic neural networks as well as decision trees are capable of accurate predictions of both hydrophilic and lipid matrix tablets dissolution profiles. Elman neural networks were compared to most frequently used static network, Multi-layered perceptron, and superiority of Elman networks have been demonstrated. Developed methods allow simple, yet very precise way of drug release predictions for both hydrophilic and lipid matrix tablets having controlled drug release.

Keywords:
Matrix tablets / Neural networks / Decision trees / Drug release modeling / Controlled release
Source:
International Journal of Pharmaceutics, 2012, 428, 1-2, 57-67
Publisher:
  • Elsevier Science BV, Amsterdam
Funding / projects:
  • Advanced technologies for controlled release from solid drug delivery systems (RS-34007)

DOI: 10.1016/j.ijpharm.2012.02.031

ISSN: 0378-5173

PubMed: 22402474

WoS: 000302364600008

Scopus: 2-s2.0-84859428478
[ Google Scholar ]
30
21
URI
https://farfar.pharmacy.bg.ac.rs/handle/123456789/1705
Collections
  • Radovi istraživača / Researchers’ publications
Institution/Community
Pharmacy
TY  - JOUR
AU  - Petrović, Jelena
AU  - Ibrić, Svetlana
AU  - Betz, Gabriele
AU  - Đurić, Zorica
PY  - 2012
UR  - https://farfar.pharmacy.bg.ac.rs/handle/123456789/1705
AB  - The main objective of the study was to develop artificial intelligence methods for optimization of drug release from matrix tablets regardless of the matrix type. Static and dynamic artificial neural networks of the same topology were developed to model dissolution profiles of different matrix tablets types (hydrophilic/lipid) using formulation composition, compression force used for tableting and tablets porosity and tensile strength as input data. Potential application of decision trees in discovering knowledge from experimental data was also investigated. Polyethylene oxide polymer and glyceryl palmitostearate were used as matrix forming materials for hydrophilic and lipid matrix tablets, respectively whereas selected model drugs were diclofenac sodium and caffeine. Matrix tablets were prepared by direct compression method and tested for in vitro dissolution profiles. Optimization of static and dynamic neural networks used for modeling of drug release was performed using Monte Carlo simulations or genetic algorithms optimizer. Decision trees were constructed following discretization of data. Calculated difference (f(1)) and similarity (f(2)) factors for predicted and experimentally obtained dissolution profiles of test matrix tablets formulations indicate that Elman dynamic neural networks as well as decision trees are capable of accurate predictions of both hydrophilic and lipid matrix tablets dissolution profiles. Elman neural networks were compared to most frequently used static network, Multi-layered perceptron, and superiority of Elman networks have been demonstrated. Developed methods allow simple, yet very precise way of drug release predictions for both hydrophilic and lipid matrix tablets having controlled drug release.
PB  - Elsevier Science BV, Amsterdam
T2  - International Journal of Pharmaceutics
T1  - Optimization of matrix tablets controlled drug release using Elman dynamic neural networks and decision trees
VL  - 428
IS  - 1-2
SP  - 57
EP  - 67
DO  - 10.1016/j.ijpharm.2012.02.031
ER  - 
@article{
author = "Petrović, Jelena and Ibrić, Svetlana and Betz, Gabriele and Đurić, Zorica",
year = "2012",
abstract = "The main objective of the study was to develop artificial intelligence methods for optimization of drug release from matrix tablets regardless of the matrix type. Static and dynamic artificial neural networks of the same topology were developed to model dissolution profiles of different matrix tablets types (hydrophilic/lipid) using formulation composition, compression force used for tableting and tablets porosity and tensile strength as input data. Potential application of decision trees in discovering knowledge from experimental data was also investigated. Polyethylene oxide polymer and glyceryl palmitostearate were used as matrix forming materials for hydrophilic and lipid matrix tablets, respectively whereas selected model drugs were diclofenac sodium and caffeine. Matrix tablets were prepared by direct compression method and tested for in vitro dissolution profiles. Optimization of static and dynamic neural networks used for modeling of drug release was performed using Monte Carlo simulations or genetic algorithms optimizer. Decision trees were constructed following discretization of data. Calculated difference (f(1)) and similarity (f(2)) factors for predicted and experimentally obtained dissolution profiles of test matrix tablets formulations indicate that Elman dynamic neural networks as well as decision trees are capable of accurate predictions of both hydrophilic and lipid matrix tablets dissolution profiles. Elman neural networks were compared to most frequently used static network, Multi-layered perceptron, and superiority of Elman networks have been demonstrated. Developed methods allow simple, yet very precise way of drug release predictions for both hydrophilic and lipid matrix tablets having controlled drug release.",
publisher = "Elsevier Science BV, Amsterdam",
journal = "International Journal of Pharmaceutics",
title = "Optimization of matrix tablets controlled drug release using Elman dynamic neural networks and decision trees",
volume = "428",
number = "1-2",
pages = "57-67",
doi = "10.1016/j.ijpharm.2012.02.031"
}
Petrović, J., Ibrić, S., Betz, G.,& Đurić, Z.. (2012). Optimization of matrix tablets controlled drug release using Elman dynamic neural networks and decision trees. in International Journal of Pharmaceutics
Elsevier Science BV, Amsterdam., 428(1-2), 57-67.
https://doi.org/10.1016/j.ijpharm.2012.02.031
Petrović J, Ibrić S, Betz G, Đurić Z. Optimization of matrix tablets controlled drug release using Elman dynamic neural networks and decision trees. in International Journal of Pharmaceutics. 2012;428(1-2):57-67.
doi:10.1016/j.ijpharm.2012.02.031 .
Petrović, Jelena, Ibrić, Svetlana, Betz, Gabriele, Đurić, Zorica, "Optimization of matrix tablets controlled drug release using Elman dynamic neural networks and decision trees" in International Journal of Pharmaceutics, 428, no. 1-2 (2012):57-67,
https://doi.org/10.1016/j.ijpharm.2012.02.031 . .

DSpace software copyright © 2002-2015  DuraSpace
About FarFaR - Pharmacy Repository | Send Feedback

OpenAIRERCUB
 

 

All of DSpaceCommunitiesAuthorsTitlesSubjectsThis institutionAuthorsTitlesSubjects

Statistics

View Usage Statistics

DSpace software copyright © 2002-2015  DuraSpace
About FarFaR - Pharmacy Repository | Send Feedback

OpenAIRERCUB