PDF(Pubmed)
Abstract：
This study aims to optimize and evaluate drug release kinetics of Modified-Release (MR) solid dosage form of Quetiapine Fumarate MR tablets by using the Artificial Neural Networks (ANNs). In training the neural network, the drug contents of Quetiapine Fumarate MR tablet such as Sodium Citrate, Eudragit® L100 55, Eudragit® L30 D55, Lactose Monohydrate, Dicalcium Phosphate (DCP), and Glyceryl Behenate were used as variable input data and Drug Substance Quetiapine Fumarate, Triethyl Citrate, and Magnesium Stearate were used as constant input data for the formulation of the tablet. The in-vitro dissolution profiles of Quetiapine Fumarate MR tablets at ten different time points were used as a target data. Several layers together build the neural network by connecting the input data with the output data via weights, these weights show importance of input nodes. The training process optimises the weights of the drug product excipients to achieve the desired drug release through the simulation process in MATLAB software. The percentage drug release of predicted formulation matched with the manufactured formulation using the similarity factor (f2), which evaluates network efficiency. The ANNs have enormous potential for rapidly optimizing pharmaceutical formulations with desirable performance characteristics.
摘要：
本研究旨在通过使用人工神经网络（ANN）来优化和评估富马酸喹硫平（MR）固体剂型MR片剂的药物释放动力学。在训练神经网络时，富马酸喹硫平MR片剂的药物含量，如柠檬酸钠，Eudragit®L10055,Eudragit®L30D55,乳糖一水合物,磷酸二钙(DCP),和二十二酸甘油酯用作可变输入数据，富马酸喹硫平，柠檬酸三乙酯,和硬脂酸镁用作片剂配方的恒定输入数据。富马酸喹硫平MR片剂在10个不同时间点的体外溶出曲线被用作目标数据。通过权重将输入数据与输出数据连接，几层一起构建神经网络，这些权重显示了输入节点的重要性。该训练过程通过MATLAB软件中的模拟过程,优化药品辅料的重量以实现所需的药物释放。预测制剂的药物释放百分比与使用相似因子(f2)的制造制剂相匹配,它评估网络效率。ANN具有快速优化具有所需性能特征的药物制剂的巨大潜力。
