Preparation of controlled porosity osmotic pump tablets for salvianolic acid and optimization of the formulation using an artificial neural network method

Abstract

In this paper controlled porosity osmotic pump tablets (CPOPT) for salvianolic acid (SA) were prepared and optimized with experimental design methods including an artificial neutral network (ANN) method. Three causal factors, i.e., drug, osmotic pressure promoting agent rate, PEG400 content in coating solution and coating weight, were evaluated based on their effects on drug release rate. The linear correlation coefficient of the accumulative amount of drug release and the time of 12 h, r( Y 1), and the sum of the absolute value between measured and projected values, Y 2, were used as outputs to optimize the formulation. The weight expression Y=(1− Y 1) 2+ Y 2 2 was used in the calculation. Furthermore, the ANN and uniform design gave similar optimization results, but ANN projected the outputs better than the uniform design. This paper showed that the release rate of salvianolic acid B and that of the total salvianolic acid was consistent in the optimized formulation.