Artificial neural networks as alternative tool for minimizing error predictions in manufacturing ultradeformable nanoliposome formulations.

This work was aimed at determining the feasibility of artificial neural networks (ANN) by implementing backpropagation algorithms with default settings to generate better predictive models than multiple linear regression (MLR) analysis. The study was hypothesized on timolol-loaded liposomes. As tutorial data for ANN, causal factors were used, which were fed into the computer program. The number of training cycles has been identified in order to optimize the performance of the ANN. The optimization was performed by minimizing the error between the predicted and real response values in the training step. The results showed that training was stopped at 10 000 training cycles with 80% of the pattern values, because at this point the ANN generalizes better. Minimum validation error was achieved at 12 hidden neurons in a single layer. MLR has great prediction ability, with errors between predicted and real values lower than 1% in some of the parameters evaluated. Thus, the performance of this model was compared to that of the MLR using a factorial design. Optimal formulations were identified by minimizing the distance among measured and theoretical parameters, by estimating the prediction errors. Results indicate that the ANN shows much better predictive ability than the MLR model. These findings demonstrate the increased efficiency of the combination of ANN and design of experiments, compared to the conventional MLR modeling techniques.

Robust optimization of alginate-Carbopol 940 bead formulations.

Formulation process is a very complex activity which sometimes implicates taking decisions about parameters or variables to obtain the best results in a high variability or uncertainty context. Therefore, robust optimization tools can be very useful for obtaining high quality formulations. This paper proposes the optimization of different responses through the robust Taguchi method. Each response was evaluated like a noise variable, allowing the application of Taguchi techniques to obtain a response under the point of view of the signal to noise ratio. A L(18) Taguchi orthogonal array design was employed to investigate the effect of eight independent variables involved in the formulation of alginate-Carbopol beads. Responses evaluated were related to drug release profile from beads (t(50%) and AUC), swelling performance, encapsulation efficiency, shape and size parameters. Confirmation tests to verify the prediction model were carried out and the obtained results were very similar to those predicted in every profile. Results reveal that the robust optimization is a very useful approach that allows greater precision and accuracy to the desired value.