Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method for performing quality control on traditional Chinese medicine by adopting SVM (support vector machine) technique

A technology for traditional Chinese medicine preparations and traditional Chinese medicines, which is applied in measurement devices, instruments, character and pattern recognition, etc., can solve the problems of insufficient sensitivity, quality deviation, and inability to directly predict the quality of independent unknown samples, so as to achieve sensitive quality control, ensure safety, and accuracy. The effect of quality control

Inactive Publication Date: 2017-03-22
TIANJIN UNIV OF TRADITIONAL CHINESE MEDICINE
View PDF1 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, fingerprint similarity evaluation is a qualitative evaluation method, which depends on the distribution ratio of chemical components, and it is not sensitive enough to evaluate the quality deviation caused by the difference in component content, and at the same time, some studies have shown that it may misjudge unqualified products are qualified
In addition, applying principal component analysis (PCA) or cluster analysis (HCA) combined with similarity assessment can improve the accuracy of quality control, however, PCA or HCA are widely used as classification methods and they cannot directly predict the quality of independent unknown samples

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for performing quality control on traditional Chinese medicine by adopting SVM (support vector machine) technique
  • Method for performing quality control on traditional Chinese medicine by adopting SVM (support vector machine) technique
  • Method for performing quality control on traditional Chinese medicine by adopting SVM (support vector machine) technique

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0039] Using SVM technology to identify the manufacturer, process and dosage form of Xuefu Zhuyu Pills:

[0040] 1. Reagents: methanol (Sigma, USA); glacial acetic acid (Tianjin Concord Technology Co., Ltd.); all are chromatographically pure. Watsons Distilled Water; Xuefu Zhuyu Pills (Heilongjiang Shenge Pharmaceutical Co., Ltd., Xiaomi Pills); Xuefu Zhuyu Pills (Yaodu Pharmaceutical Group Co., Ltd., Shuiwan); Ltd., Honey Pill);

[0041] 2. Chromatographic conditions: Diamonsil C18(2) (5 μm 200×4.6 mm) chromatographic column; mobile phase is 1% glacial acetic acid aqueous solution (A)-methanol (B), gradient elution: 0-10min, 10%-25 %B; 10-35min 25%-55%B; 35-65min, 55%-100%; 65-70min, 100%-10%B; 70-75min, 10%B; flow rate 0.5mL / min, column temperature 35°C, detection wavelength 270 nm, injection volume 5 μL.

[0042] 3. Preparation of sample solution: Cut each batch of Xuefu Zhuyu Pills into small pieces, weigh 5g, add methanol for reflux extraction twice, add 10 times the a...

Embodiment 2

[0046] Using SVM technology to distinguish whether the Kudiezi injection is expired or not handled properly:

[0047] 1. Reagents: Acetonitrile was purchased from Sigma (USA), formic acid was purchased from Tianjin Yuanli Chemical Co., Ltd., and glacial acetic acid was purchased from Tianjin Concord Technology Co., Ltd., all of which were chromatographically pure. Distilled water was purchased from Guangzhou Watsons Food and Beverage Co., Ltd. Kudiezi injection was provided by Jilin Tonghua Huaxia Pharmaceutical Co., Ltd. Standard products of uridine, guanosine and apigenin 7-O-β-D glucuronide were purchased from Tianjin Shilan Technology Co., Ltd. Standard products of monocaffeoyl tartaric acid were purchased from Shanghai Yuanye Biotechnology Co., Ltd. Standards of adenosine, chlorogenic acid, and cichoric acid were purchased from China National Institutes for Food and Drug Control, and luteolin-7-O-β-D glucuronide was provided by Tonghua Chemical Pharmaceutical Company . ...

Embodiment 3

[0054] Practical application:

[0055] The present invention further compares and analyzes the application of the commonly used traditional Chinese medicine and its preparation quality evaluation system-Chinese medicine chromatographic fingerprint similarity evaluation software and the newly proposed SVM technology in the quality evaluation of Kudiezi injection. First, use the control fingerprint generated in Example 2 to check the similarity of the chromatographic data of the expired injection and the Kudiezi injection after high temperature and light treatment. The chromatograms are shown in Figure 7 , Figure 8 , Figure 9 , it can be seen that all 11 characteristic peaks exist in the samples to be tested, indicating that there is no difference between all the samples to be tested and the qualified Kudiezi injection, that is, the use of fingerprint technology cannot distinguish whether the injection is expired or improperly processed. The prediction rate of using SVM tec...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses a novel practical support vector machine (SVM) technique used in quality control on a traditional Chinese medicine. The support vector machine (SVM) is a supervised machine learning technique based on Vapnik chervonenks dimensions and the structural risk minimization inductive principle, and is characterized by expressing a sample as a point in a higher dimensional space through an optimal kernel function, generating a hyperplane boundary and realizing sample classification; and different from other machine learning techniques, the SVM can minimize sampling point errors and improve the generalization capability of a model based on the structural risk minimization inductive principle. The SVM technique provided by the invention can detect the quality of a traditional Chinese medicine more sensitively and accurately than fingerprint chromatography, so that similarity evaluation limitations of the fingerprint chromatography are effectively compensated for, thereby achieving more sensitive and reliable quality control on the traditional Chinese medicine.

Description

technical field [0001] The invention involves using a liquid chromatography system to collect data, searching for common characteristic peaks, and then using support vector machine (SVM) technology to evaluate the quality of different traditional Chinese medicines. Background technique [0002] Traditional Chinese medicine and its preparations are widely used clinically and play an important role in the treatment of human diseases, but they are also accompanied by safety risks. Many adverse drug reactions have been reported in recent years. The inevitable requirement of the clinical safety of traditional Chinese medicine. Fingerprint analysis of traditional Chinese medicine is a comprehensive qualitative method for species identification and quality evaluation. In addition, fingerprint can fully reflect the relative relationship between components in the complex system of traditional Chinese medicine preparations, and is suitable for controlling the quality stability of trad...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G01N30/02G06K9/62
CPCG01N30/02G06F18/2411
Inventor 李遇伯邹敬韬杨彬原旭伟王玉明王媛董文颖
Owner TIANJIN UNIV OF TRADITIONAL CHINESE MEDICINE
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products