Optimization and prediction of ibuprofen release from 3D DLP printlets using artificial neural networks
Autori
Madžarević, MarijanaMedarević, Đorđe
Vulović, Aleksandra
Šušteršič, Tijana
Đuriš, Jelena
Filipović, Nenad
Ibrić, Svetlana
Članak u časopisu (Objavljena verzija)
CC BY
Metapodaci
Prikaz svih podataka o dokumentuApstrakt
The aim of this work was to investigate eects of the formulation factors on tablet printability as well as to optimize and predict extended drug release from cross-linked polymeric ibuprofen printlets using an artificial neural network (ANN). Printlets were printed using digital light processing (DLP) technology from formulations containing polyethylene glycol diacrylate, polyethylene glycol, and water in concentrations according to D-optimal mixture design and 0.1% w/w riboflavin and 5% w/w ibuprofen. It was observed that with higher water content longer exposure time was required for successful printing. For understanding the eects of excipients and printing parameters on drug dissolution rate in DLP printlets two dierent neural networks were developed with using two commercially available softwares. After comparison of experimental and predicted values of in vitro dissolution at the corresponding time points for optimized formulation, the R2 experimental vs. predicted value was 0.98...11 (neural network 1) and 0.9960 (neural network 2). According to dierence f1 and similarity factor f2 (f1 = 14.30 and f2 = 52.15) neural network 1 with supervised multilayer perceptron, backpropagation algorithm, and linear activation function gave a similar dissolution profile to obtained experimental results, indicating that adequate ANN is able to set out an input–output relationship in DLP printing of pharmaceutics.
Ključne reči:
Additive manufacturing / Digital light processing technology / Neural networks / Optimization / Prediction / Printlets / Three-dimensional printingIzvor:
Pharmaceutics, 2019, 11, 10, 1-16Izdavač:
- MDPI
Finansiranje / projekti:
- Razvoj proizvoda i tehnologija koje obezbeđuju željeno oslobađanje lekovitih supstanci iz čvrstih farmaceutskih oblika (RS-MESTD-Technological Development (TD or TR)-34007)
- Primena biomedicinskog inženjeringa u pretkliničkoj i kliničkoj praksi (RS-MESTD-Integrated and Interdisciplinary Research (IIR or III)-41007)
- Metode modeliranja na više skala sa primenama u biomedicini (RS-MESTD-Basic Research (BR or ON)-174028)
DOI: 10.3390/pharmaceutics11100544
ISSN: 1999-4923
WoS: 000498392300057
Scopus: 2-s2.0-85074050369
Institucija/grupa
PharmacyTY - JOUR AU - Madžarević, Marijana AU - Medarević, Đorđe AU - Vulović, Aleksandra AU - Šušteršič, Tijana AU - Đuriš, Jelena AU - Filipović, Nenad AU - Ibrić, Svetlana PY - 2019 UR - https://farfar.pharmacy.bg.ac.rs/handle/123456789/3466 AB - The aim of this work was to investigate eects of the formulation factors on tablet printability as well as to optimize and predict extended drug release from cross-linked polymeric ibuprofen printlets using an artificial neural network (ANN). Printlets were printed using digital light processing (DLP) technology from formulations containing polyethylene glycol diacrylate, polyethylene glycol, and water in concentrations according to D-optimal mixture design and 0.1% w/w riboflavin and 5% w/w ibuprofen. It was observed that with higher water content longer exposure time was required for successful printing. For understanding the eects of excipients and printing parameters on drug dissolution rate in DLP printlets two dierent neural networks were developed with using two commercially available softwares. After comparison of experimental and predicted values of in vitro dissolution at the corresponding time points for optimized formulation, the R2 experimental vs. predicted value was 0.9811 (neural network 1) and 0.9960 (neural network 2). According to dierence f1 and similarity factor f2 (f1 = 14.30 and f2 = 52.15) neural network 1 with supervised multilayer perceptron, backpropagation algorithm, and linear activation function gave a similar dissolution profile to obtained experimental results, indicating that adequate ANN is able to set out an input–output relationship in DLP printing of pharmaceutics. PB - MDPI T2 - Pharmaceutics T1 - Optimization and prediction of ibuprofen release from 3D DLP printlets using artificial neural networks VL - 11 IS - 10 SP - 1 EP - 16 DO - 10.3390/pharmaceutics11100544 ER -
@article{ author = "Madžarević, Marijana and Medarević, Đorđe and Vulović, Aleksandra and Šušteršič, Tijana and Đuriš, Jelena and Filipović, Nenad and Ibrić, Svetlana", year = "2019", abstract = "The aim of this work was to investigate eects of the formulation factors on tablet printability as well as to optimize and predict extended drug release from cross-linked polymeric ibuprofen printlets using an artificial neural network (ANN). Printlets were printed using digital light processing (DLP) technology from formulations containing polyethylene glycol diacrylate, polyethylene glycol, and water in concentrations according to D-optimal mixture design and 0.1% w/w riboflavin and 5% w/w ibuprofen. It was observed that with higher water content longer exposure time was required for successful printing. For understanding the eects of excipients and printing parameters on drug dissolution rate in DLP printlets two dierent neural networks were developed with using two commercially available softwares. After comparison of experimental and predicted values of in vitro dissolution at the corresponding time points for optimized formulation, the R2 experimental vs. predicted value was 0.9811 (neural network 1) and 0.9960 (neural network 2). According to dierence f1 and similarity factor f2 (f1 = 14.30 and f2 = 52.15) neural network 1 with supervised multilayer perceptron, backpropagation algorithm, and linear activation function gave a similar dissolution profile to obtained experimental results, indicating that adequate ANN is able to set out an input–output relationship in DLP printing of pharmaceutics.", publisher = "MDPI", journal = "Pharmaceutics", title = "Optimization and prediction of ibuprofen release from 3D DLP printlets using artificial neural networks", volume = "11", number = "10", pages = "1-16", doi = "10.3390/pharmaceutics11100544" }
Madžarević, M., Medarević, Đ., Vulović, A., Šušteršič, T., Đuriš, J., Filipović, N.,& Ibrić, S.. (2019). Optimization and prediction of ibuprofen release from 3D DLP printlets using artificial neural networks. in Pharmaceutics MDPI., 11(10), 1-16. https://doi.org/10.3390/pharmaceutics11100544
Madžarević M, Medarević Đ, Vulović A, Šušteršič T, Đuriš J, Filipović N, Ibrić S. Optimization and prediction of ibuprofen release from 3D DLP printlets using artificial neural networks. in Pharmaceutics. 2019;11(10):1-16. doi:10.3390/pharmaceutics11100544 .
Madžarević, Marijana, Medarević, Đorđe, Vulović, Aleksandra, Šušteršič, Tijana, Đuriš, Jelena, Filipović, Nenad, Ibrić, Svetlana, "Optimization and prediction of ibuprofen release from 3D DLP printlets using artificial neural networks" in Pharmaceutics, 11, no. 10 (2019):1-16, https://doi.org/10.3390/pharmaceutics11100544 . .