Application of Design of Experiments and Multilayer Perceptrons Neural Network in the Optimization of Diclofenac Sodium Extended Release Tablets with Carbopol (R) 71G
Authorized Users Only
2010
Authors
Ivić, BrankaIbrić, Svetlana

Cvetković, Nebojša
Petrović, Aleksandra
Trajković, Svetlana
Đurić, Zorica
Article (Published version)

Metadata
Show full item recordAbstract
The purpose of the study was to screen the effects of formulation factors on the in vitro release profile of diclofenac sodium from matrix tablets using design of experiment (DOE). Formulations of diclofenac sodium tablets, with Carbopol (R) 71G as matrix substance, were optimized by artificial neural network. According to Central Composite Design, 10 formulations of diclofenac sodium matrix tablets were prepared. As network inputs, concentration of Carbopol (R) 71G and the Kollidon (R) K-25 were selected. In vitro dissolution time profiles at 5 different sampling times were chosen as responses. The independent variables and the release parameters were processed by multilayer perceptrons neural network (MLP). Results of drug release studies indicate that drug release rates vary between different formulations, with a range of 1 h to more than 8 h to complete dissolution. For two tested formulations there was no difference between experimental and MLP predicted in vitro profiles. The M L...P model was optimized. The root mean square value for the trained network was 0.07%, which indicated that the optimal MLP model was reached. The optimal tablet formulation predicted by MLP was with 23% of Carbopol (R) 710 and 0.8% of Kollidon (R) K-25. Calculated difference factor (f(1) 7.37) and similarity factor (f(2) 70.79) indicate that there is no difference between predicted and experimentally observed drug release profiles for the optimal formulation. The satisfactory prediction of drug release for optimal formulation by the MLP in this study has shown the applicability of this optimization method in modeling extended release tablet formulation.
Keywords:
matrix tablet / Carbopol 71G / extended release / diclofenac sodium / neural networkSource:
Chemical & Pharmaceutical Bulletin, 2010, 58, 7, 947-949Publisher:
- Pharmaceutical Soc Japan, Tokyo
DOI: 10.1248/cpb.58.947
ISSN: 0009-2363
PubMed: 20606343
WoS: 000279213500013
Scopus: 2-s2.0-77954261268
Collections
Institution/Community
PharmacyTY - JOUR AU - Ivić, Branka AU - Ibrić, Svetlana AU - Cvetković, Nebojša AU - Petrović, Aleksandra AU - Trajković, Svetlana AU - Đurić, Zorica PY - 2010 UR - https://farfar.pharmacy.bg.ac.rs/handle/123456789/1401 AB - The purpose of the study was to screen the effects of formulation factors on the in vitro release profile of diclofenac sodium from matrix tablets using design of experiment (DOE). Formulations of diclofenac sodium tablets, with Carbopol (R) 71G as matrix substance, were optimized by artificial neural network. According to Central Composite Design, 10 formulations of diclofenac sodium matrix tablets were prepared. As network inputs, concentration of Carbopol (R) 71G and the Kollidon (R) K-25 were selected. In vitro dissolution time profiles at 5 different sampling times were chosen as responses. The independent variables and the release parameters were processed by multilayer perceptrons neural network (MLP). Results of drug release studies indicate that drug release rates vary between different formulations, with a range of 1 h to more than 8 h to complete dissolution. For two tested formulations there was no difference between experimental and MLP predicted in vitro profiles. The M LP model was optimized. The root mean square value for the trained network was 0.07%, which indicated that the optimal MLP model was reached. The optimal tablet formulation predicted by MLP was with 23% of Carbopol (R) 710 and 0.8% of Kollidon (R) K-25. Calculated difference factor (f(1) 7.37) and similarity factor (f(2) 70.79) indicate that there is no difference between predicted and experimentally observed drug release profiles for the optimal formulation. The satisfactory prediction of drug release for optimal formulation by the MLP in this study has shown the applicability of this optimization method in modeling extended release tablet formulation. PB - Pharmaceutical Soc Japan, Tokyo T2 - Chemical & Pharmaceutical Bulletin T1 - Application of Design of Experiments and Multilayer Perceptrons Neural Network in the Optimization of Diclofenac Sodium Extended Release Tablets with Carbopol (R) 71G VL - 58 IS - 7 SP - 947 EP - 949 DO - 10.1248/cpb.58.947 UR - https://hdl.handle.net/21.15107/rcub_farfar_1401 ER -
@article{ author = "Ivić, Branka and Ibrić, Svetlana and Cvetković, Nebojša and Petrović, Aleksandra and Trajković, Svetlana and Đurić, Zorica", year = "2010", abstract = "The purpose of the study was to screen the effects of formulation factors on the in vitro release profile of diclofenac sodium from matrix tablets using design of experiment (DOE). Formulations of diclofenac sodium tablets, with Carbopol (R) 71G as matrix substance, were optimized by artificial neural network. According to Central Composite Design, 10 formulations of diclofenac sodium matrix tablets were prepared. As network inputs, concentration of Carbopol (R) 71G and the Kollidon (R) K-25 were selected. In vitro dissolution time profiles at 5 different sampling times were chosen as responses. The independent variables and the release parameters were processed by multilayer perceptrons neural network (MLP). Results of drug release studies indicate that drug release rates vary between different formulations, with a range of 1 h to more than 8 h to complete dissolution. For two tested formulations there was no difference between experimental and MLP predicted in vitro profiles. The M LP model was optimized. The root mean square value for the trained network was 0.07%, which indicated that the optimal MLP model was reached. The optimal tablet formulation predicted by MLP was with 23% of Carbopol (R) 710 and 0.8% of Kollidon (R) K-25. Calculated difference factor (f(1) 7.37) and similarity factor (f(2) 70.79) indicate that there is no difference between predicted and experimentally observed drug release profiles for the optimal formulation. The satisfactory prediction of drug release for optimal formulation by the MLP in this study has shown the applicability of this optimization method in modeling extended release tablet formulation.", publisher = "Pharmaceutical Soc Japan, Tokyo", journal = "Chemical & Pharmaceutical Bulletin", title = "Application of Design of Experiments and Multilayer Perceptrons Neural Network in the Optimization of Diclofenac Sodium Extended Release Tablets with Carbopol (R) 71G", volume = "58", number = "7", pages = "947-949", doi = "10.1248/cpb.58.947", url = "https://hdl.handle.net/21.15107/rcub_farfar_1401" }
Ivić, B., Ibrić, S., Cvetković, N., Petrović, A., Trajković, S.,& Đurić, Z.. (2010). Application of Design of Experiments and Multilayer Perceptrons Neural Network in the Optimization of Diclofenac Sodium Extended Release Tablets with Carbopol (R) 71G. in Chemical & Pharmaceutical Bulletin Pharmaceutical Soc Japan, Tokyo., 58(7), 947-949. https://doi.org/10.1248/cpb.58.947 https://hdl.handle.net/21.15107/rcub_farfar_1401
Ivić B, Ibrić S, Cvetković N, Petrović A, Trajković S, Đurić Z. Application of Design of Experiments and Multilayer Perceptrons Neural Network in the Optimization of Diclofenac Sodium Extended Release Tablets with Carbopol (R) 71G. in Chemical & Pharmaceutical Bulletin. 2010;58(7):947-949. doi:10.1248/cpb.58.947 https://hdl.handle.net/21.15107/rcub_farfar_1401 .
Ivić, Branka, Ibrić, Svetlana, Cvetković, Nebojša, Petrović, Aleksandra, Trajković, Svetlana, Đurić, Zorica, "Application of Design of Experiments and Multilayer Perceptrons Neural Network in the Optimization of Diclofenac Sodium Extended Release Tablets with Carbopol (R) 71G" in Chemical & Pharmaceutical Bulletin, 58, no. 7 (2010):947-949, https://doi.org/10.1248/cpb.58.947 ., https://hdl.handle.net/21.15107/rcub_farfar_1401 .