Data mining in traditional Chinese medicine product quality review.
10.19540/j.cnki.cjcmm.20221128.301
- Author:
Sheng ZHANG
1
;
Hou-Liu CHEN
2
;
Hai-Bin QU
1
Author Information
1. Pharmaceutical Informatics Institute, College of Pharmaceutical Sciences, Zhejiang University Hangzhou 310058, China Innovation Center in Zhejiang University, State Key Laboratory of Component-Based Chinese Medicine Hangzhou 310058, China.
2. Hangzhou XianTeng Data Technology Co., Ltd. Hangzhou 311100, China.
- Publication Type:Journal Article
- Keywords:
data mining;
product quality review;
risk evaluation;
traditional Chinese medicine manufacturing
- MeSH:
Medicine, Chinese Traditional;
Drugs, Chinese Herbal;
Data Mining/methods*;
Quality Control;
Technology, Pharmaceutical
- From:
China Journal of Chinese Materia Medica
2023;48(5):1264-1272
- CountryChina
- Language:Chinese
-
Abstract:
The traditional Chinese medicine(TCM) enterprises have accumulated a large amount of product quality review(PQR) data. Mining these data can reveal the hidden knowledge in production and helps improve pharmaceutical manufacturing technology. However, there are few studies involving the mining of PQR data and thus enterprises lack the guidance to analyze the data. This study proposed a method to mine the PQR data, which consisted of 4 functional modules: data collection and preprocessing, risk classification of variables, risk evaluation by batches, and the regression analysis of quality. Further, we carried out a case study of the formulation process of a TCM product to illustrate the method. In the case study, the data of 398 batches of products during 2019-2021 were collected, which contained 65 process variables. The risks of variables were classified according to the process performance index. The risk of each batch was analyzed through short-term and long-term evaluation, and the critical variables with the strongest impact on the product quality were identified by partial least square regression. The results showed that 1 variable and 13 batches were of high risk, and the critical process variable was the quality of the intermediates. The proposed method enables enterprises to comprehensively mine the PQR data and helps to enhance the process understanding and improve the quality control.
