Estimation of Betamethasone Release Profiles from an in Situ Forming System Based on the Biodegradable Polymer Using Artificial Neural Networks

Abstract

In this paper, three feed-forward neural networks including Multi-Layer Perceptron (MLP), Radial Basis Function network (RBFN) and Generalized Regression Neural Network (GRNN) are employed to estimate the release profile of betamethasone (BTM) and betamethasone acetate (BTMA). To accomplish this task, three features are extracted from each release profile using the nonlinear principal component analysis (NLPCA) technique, constituting the outputs of the neural network. The drug loaded formulation parameters are the input vectors of the artificial neural networks (ANNs) which include drug concentration, gamma irradiation, additive substance and type of drug (BTMA or BTM). Regarding the drug loaded formulation parameters as the input vectors and the extracted features as the output vectors, leave-one-out cross validation (L.O.O.) approach are used to train each neural network. Several simulations are presented to compare the potential of each neural network. It is demonstrated that the MLP is more reliable and efficient tool and has better performance in estimation of BTM and BTMA release profile than GRNN and RBF networks.