偏最小二乘在中药药性判别中的应用

山东大学学报(医学版) ›› 2012, Vol. 50 ›› Issue (1): 151-.

偏最小二乘在中药药性判别中的应用

1. 山东大学公共卫生学院流行病与卫生统计学研究所, 济南 250012;
2. 山东中医药大学药学院, 济南 250355

收稿日期:2011-06-17 出版日期:2012-01-10 发布日期:2012-01-10
通讯作者: 薛付忠(1964- ),男,博士研究生,博士生导师,主要从事中药药性统计分析方法研究。Email: xuefzh@sdu.edu.cn。
作者简介:刘文慧(1987- ),女,硕士研究生,主要从事中药药性识别的统计模式识别模型研究。
基金资助:
国家重点基础研究发展计划(973计划)课题:中药药性理论相关基础问题研究(2007CB512601)

Partial least squares in the discrimination of traditional
Chinese herbal medicine property

LIU Wen-hui1, LI YU1, JI Yu-jia2, WANG Peng2, ZHANG Yong-qing2, XUE Fu-zhong1

1. Institute of Epidemiology and Health Statistics, School of Public Health, Shandong University, Jinan 250012, China;
2. School of Pharmacy, Shandong University of Traditional Chinese Medicine, Jinan 250355, China

Received:2011-06-17 Online:2012-01-10 Published:2012-01-10

摘要/Abstract

摘要：

目的探讨将偏最小二乘法用于中药药性判别的可行性。方法收集《中华本草》中收录的药性明确、功效主治明确的植物性中药1725种,利用基于偏最小二乘的两种方法建立药性识别模型,用组内回代、外推预测、交叉验证等方式评价模型。结果基于偏最小二乘法的两种模型的判别效果与原来判定结果符合率分别为9275％、94-67％,两种方法的外推预测正确率分别为85-51％、8986％,而重复10次的5折交叉验证正确率分别达到了88-28％、9046％。结论基于中药的功效主治,偏最小二乘法能够准确判别药性且模型稳定好,能够有效解决多重共线性等问题,为中药药性的有效判别提供了新的思路和方法。

关键词: 偏最小二乘;中药药性;判别分析;线性判别

Abstract:

Objective To investigate the feasibility of partial least squares (PLS) in the discrimination of traditional Chinese herbal medicine property(CHMP). Methods Information on original effects of 1725 kinds of Chinese herbal medicine (CHM) was collected from “Chinese Herbal Medicine”. Two PLS-based methods were performed to build the discrimination model, which was evaluated by consistent homology rate, extrapolated prediction and 5 fold cross validation. Results Using the two PLS-based methods, consistent homology rates of property with original discriminant results were 92-75％ and 94-67％, respectively. Predictive accuracies of testing set were 8551％ and 8986％, respectively. 10-iteration 5-fold cross validation accuracy were 88-28％ and 90-46％, respectively. Conclusion According to original effects of CHM, the PLSbased methods can be useful in discriminating CHMP, with high accuracy and stability, and effectively deal with multicollinearity of multivariate, providing a new idea and method for discrimination of CHMP.

Key words: Partial least squares; Chinese herbal medicine property; Discriminant analysis; Linear discrimination

中图分类号:

R282-5

刘文慧1,李雨1,纪玉佳2,王鹏2,张永清2,薛付忠1. 偏最小二乘在中药药性判别中的应用[J]. 山东大学学报(医学版), 2012, 50(1): 151-.

LIU Wen-hui1, LI YU1, JI Yu-jia2, WANG Peng2, ZHANG Yong-qing2, XUE Fu-zhong1. Partial least squares in the discrimination of traditional
Chinese herbal medicine property[J]. JOURNAL OF SHANDONG UNIVERSITY (HEALTH SCIENCES), 2012, 50(1): 151-.

参考文献

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed