摘要
目的提出伸缩移动窗口相似度结合贝叶斯法通过拉曼光谱技术对弱主药信号药品的真假进行快速判别。方法采用伸缩移动窗口相似度方法,以弱主药信号药品的药用活性成分(API)的拉曼光谱峰宽为参照,动态调整窗口的大小。在窗口内,分别计算API的拉曼光谱峰信号与药品拉曼光谱的相似度,以及药品与辅料的拉曼光谱相似度,选择那些突出API拉曼光谱峰信号对弱主药信号药品的拉曼光谱信号有贡献的窗口作为贝叶斯判别模型的变量,进而构建弱主药信号药品真假判别模型。结果本研究构建的弱主药信号药品真假判别模型对弱主药信号药品的真假准确识别率为94.7%,对验证集样本准确识别率为95.6%。结论基于伸缩移动窗口相似度与贝叶斯算法构建的贝叶斯判别模型可以对弱主药信号药品的真假进行快速判别。
Objective To propose scalable moving-window similarity combined with Bayesian for rapid discriminating low active pharmaceutical ingredient（API）signal drugs（LAPIDs）.Methods The scalable moving-window similarity method was employed by setting the window size dynamically according to API′s peak width.In each window,the correlation coefficient（CC）of API′s peak spectrum signal with LAPID′s spectrum and LAPID′s spectrum with excipient′s spectrum were calculated respectively.The LAPIDs discrimination model was established by choosing windows with most contribution of the API spectral signal to the LAPID spectrum as variables for Bayesian discriminant model.Results The accuracy rate of LAPIDs discrimination model for discriminating LAPIDs was 94.7%.The accuracy rate of the model for discriminating testing samples was 95.6%.Conclusion Bayesian discrimination model based on scalable moving-window similarity and Bayesian algorithm can quickly discriminate LAPIDs.
作者
陈秀娟
陈辉
魏航
柳艳
陆峰
CHEN Xiujuan;CHEN Hui;WEI Hang;LIU Yan;LU Feng(School of Pharmacy ,Second Military Medical University , Shanghai, 200433 , Chin;Shanghai DiaCartra Biomedical LLC , Shanghai 200070 , China;School of Medical Information Engineering,Guangzhou University of Chinese Medicine, Guangzhou, 510006, China)
出处
《药学实践杂志》
CAS
2018年第3期210-214,共5页
Journal of Pharmaceutical Practice
基金
国家自然科学基金(81573598)
国家重大科学仪器设备开发专项"便携式薄层色谱-拉曼光谱联用仪及其药品快检支撑系统"(2012YQ18013203)
关键词
伸缩移动窗口相似度
贝叶斯判别
拉曼光谱
药品真假判别
scalable moving-window similarity
Bayesian discrimination
Raman spectroscopy
drug authenticity dis-crimination
