Optimization of transdermal and transmucosal drug delivery systems utilizing artificial neural networks

利用人工神经网络优化透皮和跨粘膜给药系统

• 批准号: 12672096
• 负责人: TAKAYAMA Kozo
• 金额: $ 1.86万
• 依托单位: Hoshi University
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Scientific Research (C)
• 财政年份: 2000
• 资助国家: 日本
• 起止时间: 2000 至 2002
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-12672096/
• 关键词: Optimization; Artificial neural network; Response surface method; Formulation; Transdermal absorption; Chemical enhancer; Drug delivery; Ketoprofen; 薬物送達; ケトプロフェン; メントール誘導体; 構造活性相関; 刺激性

A pharmaceutical formulation is composed of several formulation factors and process variables. Several responses relating to the effectiveness, usefulness, 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. A multi-objective simultaneous optimization method incorporating an artificial neural network (ANN) was developed. The method was applied to the optimization of ketoprofen hydrogel formulations including 1-O-ethyl-3-n-butylcyclohexanol as absorption enhancer. ANNs are being increasingly used in pharmaceutical research to predict the nonlinear relationship between causal factors and response variables. The observed results of several characteristics in the optimum formulations coincided well with the predictions, suggesting superior function of the ANN approach.

药物配方由多个配方因素和工艺变量组成。必须同时优化与有效性、有用性、稳定性和安全性有关的几个反应。因此，需要专业知识和经验来设计可接受的药物配方。响应面方法(RSM)已被广泛用于选择可接受的药物配方。然而，基于RSM中常用的二阶多项式方程对药物反应的预测往往局限于低水平，导致对最优配方的估计不佳。提出了一种结合人工神经网络(ANN)的多目标同时优化方法。将该方法应用于以1-O-乙基-3-正丁基环己醇为吸收促进剂的酮洛芬水凝胶处方的优化。人工神经网络在药物研究中越来越多地被用来预测因果因素和反应变量之间的非线性关系。最优配方中几个特性的观测结果与预测结果吻合较好，表明人工神经网络方法具有较好的性能。

项目成果

M.Morishita: "Elucidation of the mechanism of incorporation of insulin in controlled release systems based on complexation polymers"J.Controlled Rel.. 81. 25-32 (2002)

M.Morishita：“基于络合聚合物的控释系统中胰岛素掺入机制的阐明”J.Controlled Rel.. 81. 25-32 (2002)

小川法子: "花粉症治療を目的としたflunisolide含有持続性鼻腔用軟膏の開発"薬剤学. 63. 161-168 (2002)

Noriko Okawa：“开发含有氟尼缩松的长效鼻用软膏，用于治疗花粉症”药理学 63. 161-168 (2002)。

K.Nakamura: "Regional intestinal absorption of FITC-dextran 4,400 with nanoparticles based on β-sitosterol β-D-glucoside in rats"J.Pharm.Sci.. 92. 311-318 (2003)

K. Nakamura：“基于 β-谷甾醇 β-D-葡萄糖苷的纳米颗粒对 FITC-葡聚糖 4,400 在大鼠中的区域肠道吸收”J.Pharm.Sci.. 92. 311-318 (2003)

K. Takayama, A. Morva, M. Fujikawa, Y. Hattori, Y. Obata and T. Nagai: "Formula optimization of theophylline tablet based on artificial neural networks"J. Controlled Rel.. 68. 145-186 (2000)

K. Takayama、A. Morva、M. Fujikawa、Y. Hattori、Y. Obata 和 T. Nagai：“基于人工神经网络的茶碱片配方优化”J。

J. P. Wang, Y. Maitani, K. Takayama and T. Nagai: "In vivo evaluation of doxorubicin carried with long circulating and remote loading proliposome"Int. J. Pharm.. 203. 61-69 (2000)

J. P. Wang、Y. Maitani、K. Takayama 和 T. Nagai：“长循环和远程装载前脂质体携带的阿霉素的体内评估”Int。