Optimization of Pharmaceutical Formulations Based on Artificial Neural Networks

Abstract

A pharmaceutical formulation is composed of several formulation factors and process variables. Several responses relating to the effectiveness, usefulness and stability, as well as safety, must be optimized simultaneously. Consequently, expertise and experience are required to design acceptable pharmaceutical formulations. A response surface method (RSM) has widely been used for selecting acceptable pharmaceutical formulations. However, prediction of pharmaceutical responses based on the second-order polynomial equation commonly used in RSM is often limited to low levels, resulting in poor estimations of optimal formulations. In this review, a multi-objective simultaneous optimization method incorporating an artificial neural network (ANN) is introduced. Further, usefulness of the method is demonstrated by its application to the optimization of ketoprofen hydrogel formulations including 1-O-ethyl-3-n-butylcyclohexanol as a newly developed transdermal absorption enhancer.