Pharmaceutical Analytical Chemistry Department, Faculty of Pharmacy, Mansoura University, Mansoura, Egypt.
Pharmaceutical Analytical Chemistry Department, Faculty of Pharmacy, Al-Azhar University, Cairo, Egypt.
Spectrochim Acta A Mol Biomol Spectrosc. 2021 May 5;252:119505. doi: 10.1016/j.saa.2021.119505. Epub 2021 Jan 29.
Artificial neural networks and genetic algorithm artificial neural networks, chemometric assisted spectrophotometric models, were developed for the quantitative analysis of elbasvir and grazoprevir in their newly FDA approved pharmaceutical dosage form. The UV absorption spectra of elbasvir and grazoprevir show severe degree of overlap which caused difficulty for selecting certain spectrophotometric method with advantage of simultaneous quantitative analysis of the cited drugs. After extensive study and many experimental trials, artificial neural networks and genetic algorithm artificial neural networks were the suitable models for the quantitative analysis of studied drugs in their binary mixture. Experimental design and constructing the calibration and validation sets of the binary mixture were achieved to implement the proposed models. The models were optimized with the aid of five-levels, two factors experimental design. The designed models were successfully applied to the quantitative analysis of Zepatier® tablets. The results were statistically compared with another reported HPLC quantitative analytical method with no significant difference by applying Student t-test and variance ratio F-test.
人工神经网络和遗传算法人工神经网络，化学计量学辅助分光光度模型，被开发用于定量分析新获得 FDA 批准的药物制剂中的 Elbasvir 和 Grazoprevir。Elbasvir 和 Grazoprevir 的紫外吸收光谱有严重的重叠程度，这给选择具有同时定量分析引用药物优势的特定分光光度法带来了困难。经过广泛的研究和多次实验，人工神经网络和遗传算法人工神经网络是用于同时定量分析这两种药物的合适模型。实验设计和二元混合物的校准和验证集的构建是为了实现所提出的模型。该模型通过 5 级、2 因素实验设计进行了优化。设计的模型成功地应用于 Zepatier®片剂的定量分析。通过应用学生 t 检验和方差比 F 检验，将结果与另一种报道的 HPLC 定量分析方法进行了统计学比较，没有显著差异。
