Formula optimization of theophylline controlled-release tablet based on artificial neural networks

Formulation of the controlled-release tablet containing theophylline was op timized based on the simultaneous optimization technique in which an artifi cial neural network (ANN) was incorporated. As model formulations, 16 hinds of theophylline: tablets were prepared. The amounts of Controse, the mixtu re of hydroxypropylmethyl cellulose with lactose, cornstarch and compressio n pressure were selected as causal factors. The release profiles of theophy lline were characterized as the sum of the fast and slow release fractions. The initial weight, the rate constant in the fast release fraction and the rate constant in the slow release Fraction were estimated as release param eters. A set of release parameters and causal factors were used as tutorial data for ANN and analyzed using a computer. Based on the plasma concentrat ion profiles of theophylline predicted by the pharmacokinetic analysis in h umans. a desirable set of release parameters was provided. The simultaneous optimization was performed by minimizing the generalized distance between the predicted values of each response and the desirable one that was: optim ized individually. The optimization technique incorporating ANN showed a fa irly good agreement between the observed values of release parameters and t he predicted results. (C) 2000 Elsevier Science B.V. All rights reserved.