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.

A comparative study of stabilising effect and antioxidant activity of different antioxidants on levodopa-loaded liposomes.

The aim of this study was to evaluate the stability of levodopa liposomes co-loaded with three different antioxidants (curcumin, ascorbic acid, and superoxide dismutase (SOD)). For this purpose, multilamellar liposomes were prepared. Curcumin was added into the lipid bilayer while ascorbic acid and SOD were placed into the aqueous phase. The influence of preparation technique and surface charge were also investigated. Vesicles were characterised and free radical scavenging potential was determined. From stability study, ascorbic acid showed better stabilising effect. These co-loaded liposomes also exhibited potential radical scavenging activity where ascorbic acid played a key role. From the study of different preparation techniques and charge, we concluded that cationic liposomes made by Thin Layer Evaporation following extrusion offered the best physicochemical and stability properties. A dual mechanism of these liposomes implies the chemical stabilisation of levodopa (dose reduction) and the antioxidant effect, with a preventive effect on Parkinson's disease.

Calcium alginate microspheres containing metformin hydrochloride niosomes and chitosomes aimed for oral therapy of type 2 diabetes mellitus.

Metformin is an oral hypoglycemic agent used in the type 2 diabetes, whose poor bioavailability and short half-life make the development of effective extended-release formulations highly desirable. Different metformin-loaded chitosomal and niosomal formulations were developed and suitably characterized, but were unable to provide the desired sustained release. The entrapment of both kinds of colloidal dispersions in calcium alginate beads enabled to strongly reduce the amount of drug released at gastric level (from 18 up to a maximum of 30%), and to obtain a sustained release in simulated intestinal fluid, which was properly tuned by varying the percentage of calcium alginate in the beads. In vivo studies on rats revealed a significant improvement of metformin hypoglycemic effect when orally administered as chitosomal and even more as niosomal dispersion entrapped in alginate beads, not only with respect to the drug as such, but also to the alginate beads loaded with the plain drug. The more intense and sustained therapeutic effect with time provided by the drug-in niosomes-in alginate bead formulation could be very profitable for maintaining tight blood glucose levels over prolonged period of time after oral administration, allowing a reduction of its dose and related collateral effects, and improving patient compliance.