Simultaneous optimization based on artificial neural networks in ketoprofen hydrogel formula containing O-ethyl-3-butylcyclohexanol as percutaneous absorption enhancer.

摘要

The influence of the amounts of additives including 1-O-ethyl-3-n-butylcyclohexanol (OEBC), diisopropyl adipate (DIA), and isopropanol (IPA) on the penetration rate (R(p)) of ketoprofen from hydrogels through rat skin in vivo was investigated. Skin irritation evoked by the application of hydrogels was evaluated based on a microscopic observation of skin cross-sections. Both optimization techniques incorporating an artificial neural network (ANN) and a second-order polynomial regression analysis were applied to the optimization of ketoprofen hydrogel formulations. Findings indicated that the R(p) and total irritation score (TIS) of the skin were predicted quantitatively as a function of quantities of OEBC, DIA, and IPA, employing ANN. In contrast, the prediction ability of the polynomial regression equation was somewhat poorer compared with that of ANN. The observed results of R(p) and TIS in the optimal formulation coincided well with the predictions in the simultaneous optimization technique incorporating ANN. Copyright 2001 Wiley-Liss, Inc. and the American Pharmaceutical Association J Pharm Sci 90:1004-1014, 2001