Generalized regression neural networks in prediction of drug stability
Само за регистроване кориснике
2007
Аутори
Ibrić, SvetlanaJovanović, Milica
Đurić, Zorica
Parojčić, Jelena
Solomun, Ljiljana
Lucić, Branka
Чланак у часопису (Објављена верзија)
Метаподаци
Приказ свих података о документуАпстракт
This study had two aims. Firstly, we wanted to model the effects of the percentage of Eudragit RS PO and compression pressure as the most important process and formulation variables on the time course of drug release from extended-release matrix aspirin tablets. Secondly, we investigated the possibility of predicting drug stability and shelf-life using an artificial neural network (ANN). Ten types of matrix aspirin tablets were prepared as model formulations and were stored in stability chambers at 60 degrees C, 50 degrees C, 40 degrees C and 30 degrees C and controlled humidity. Samples were removed at predefined time points and analysed for acetylsalicylic acid (ASA) and salicylic acid (SA) content using stability-indicating HPLC. The decrease in aspirin content followed apparent zero-order kinetics. The amount of Eudragit RS PO and compression pressure were selected as causal factors. The apparent zero-order rate constants for each temperature were chosen as output variables for the... ANN. A set of output parameters and causal factors were used as training data for the generalized regression neural network (GRNN). For two additional test formulations, Arrhenius plots were constructed from the experimentally observed and GRNN-predicted results. The slopes of experimentally observed and predicted Arrhenius plots were tested for significance using Student's t-test. For test formulations, the shelf life (t(95%)) was then calculated from experimentally observed values (t(95%) 82.90 weeks), as well as from GRNN-predicted values (t(95%) 81.88 weeks). These results demonstrate that GRNN networks can be used to predict ASA content and shelf life without stability testing for formulations in which the amount of polymer and tablet hardness are within the investigated range.
Извор:
Journal of Pharmacy and Pharmacology, 2007, 59, 5, 745-750Издавач:
- Pharmaceutical Press-Royal Pharmaceutical Soc Great Britian, London
DOI: 10.1211/jpp.59.5.0017
ISSN: 0022-3573
PubMed: 17524242
WoS: 000246885300017
Scopus: 2-s2.0-34447330195
Институција/група
PharmacyTY - JOUR AU - Ibrić, Svetlana AU - Jovanović, Milica AU - Đurić, Zorica AU - Parojčić, Jelena AU - Solomun, Ljiljana AU - Lucić, Branka PY - 2007 UR - https://farfar.pharmacy.bg.ac.rs/handle/123456789/922 AB - This study had two aims. Firstly, we wanted to model the effects of the percentage of Eudragit RS PO and compression pressure as the most important process and formulation variables on the time course of drug release from extended-release matrix aspirin tablets. Secondly, we investigated the possibility of predicting drug stability and shelf-life using an artificial neural network (ANN). Ten types of matrix aspirin tablets were prepared as model formulations and were stored in stability chambers at 60 degrees C, 50 degrees C, 40 degrees C and 30 degrees C and controlled humidity. Samples were removed at predefined time points and analysed for acetylsalicylic acid (ASA) and salicylic acid (SA) content using stability-indicating HPLC. The decrease in aspirin content followed apparent zero-order kinetics. The amount of Eudragit RS PO and compression pressure were selected as causal factors. The apparent zero-order rate constants for each temperature were chosen as output variables for the ANN. A set of output parameters and causal factors were used as training data for the generalized regression neural network (GRNN). For two additional test formulations, Arrhenius plots were constructed from the experimentally observed and GRNN-predicted results. The slopes of experimentally observed and predicted Arrhenius plots were tested for significance using Student's t-test. For test formulations, the shelf life (t(95%)) was then calculated from experimentally observed values (t(95%) 82.90 weeks), as well as from GRNN-predicted values (t(95%) 81.88 weeks). These results demonstrate that GRNN networks can be used to predict ASA content and shelf life without stability testing for formulations in which the amount of polymer and tablet hardness are within the investigated range. PB - Pharmaceutical Press-Royal Pharmaceutical Soc Great Britian, London T2 - Journal of Pharmacy and Pharmacology T1 - Generalized regression neural networks in prediction of drug stability VL - 59 IS - 5 SP - 745 EP - 750 DO - 10.1211/jpp.59.5.0017 ER -
@article{ author = "Ibrić, Svetlana and Jovanović, Milica and Đurić, Zorica and Parojčić, Jelena and Solomun, Ljiljana and Lucić, Branka", year = "2007", abstract = "This study had two aims. Firstly, we wanted to model the effects of the percentage of Eudragit RS PO and compression pressure as the most important process and formulation variables on the time course of drug release from extended-release matrix aspirin tablets. Secondly, we investigated the possibility of predicting drug stability and shelf-life using an artificial neural network (ANN). Ten types of matrix aspirin tablets were prepared as model formulations and were stored in stability chambers at 60 degrees C, 50 degrees C, 40 degrees C and 30 degrees C and controlled humidity. Samples were removed at predefined time points and analysed for acetylsalicylic acid (ASA) and salicylic acid (SA) content using stability-indicating HPLC. The decrease in aspirin content followed apparent zero-order kinetics. The amount of Eudragit RS PO and compression pressure were selected as causal factors. The apparent zero-order rate constants for each temperature were chosen as output variables for the ANN. A set of output parameters and causal factors were used as training data for the generalized regression neural network (GRNN). For two additional test formulations, Arrhenius plots were constructed from the experimentally observed and GRNN-predicted results. The slopes of experimentally observed and predicted Arrhenius plots were tested for significance using Student's t-test. For test formulations, the shelf life (t(95%)) was then calculated from experimentally observed values (t(95%) 82.90 weeks), as well as from GRNN-predicted values (t(95%) 81.88 weeks). These results demonstrate that GRNN networks can be used to predict ASA content and shelf life without stability testing for formulations in which the amount of polymer and tablet hardness are within the investigated range.", publisher = "Pharmaceutical Press-Royal Pharmaceutical Soc Great Britian, London", journal = "Journal of Pharmacy and Pharmacology", title = "Generalized regression neural networks in prediction of drug stability", volume = "59", number = "5", pages = "745-750", doi = "10.1211/jpp.59.5.0017" }
Ibrić, S., Jovanović, M., Đurić, Z., Parojčić, J., Solomun, L.,& Lucić, B.. (2007). Generalized regression neural networks in prediction of drug stability. in Journal of Pharmacy and Pharmacology Pharmaceutical Press-Royal Pharmaceutical Soc Great Britian, London., 59(5), 745-750. https://doi.org/10.1211/jpp.59.5.0017
Ibrić S, Jovanović M, Đurić Z, Parojčić J, Solomun L, Lucić B. Generalized regression neural networks in prediction of drug stability. in Journal of Pharmacy and Pharmacology. 2007;59(5):745-750. doi:10.1211/jpp.59.5.0017 .
Ibrić, Svetlana, Jovanović, Milica, Đurić, Zorica, Parojčić, Jelena, Solomun, Ljiljana, Lucić, Branka, "Generalized regression neural networks in prediction of drug stability" in Journal of Pharmacy and Pharmacology, 59, no. 5 (2007):745-750, https://doi.org/10.1211/jpp.59.5.0017 . .