A novel classification method for aid decision of traditional Chinese patent medicines for stroke treatment

doi:10.1007/s11684-017-0511-1

Frontiers of Medicine

2017, Vol. 11

Issue (3): 432-439 https://doi.org/10.1007/s11684-017-0511-1

本期目录

A novel classification method for aid decision of traditional Chinese patent medicines for stroke treatment

Yufeng Zhao^1,²(

), Bo Liu³, Liyun He¹, Wenjing Bai¹, Xueyun Yu¹, Xinyu Cao^1,², Lin Luo¹, Peijing Rong⁴, Yuxue Zhao⁴, Guozheng Li^2,⁵, Baoyan Liu^2,⁵(

)

¹. Institute of Basic Research in Clinical Medicine, China Academy of Chinese Medical Sciences, Beijing 100700, China
². National Data Center of Traditional Chinese Medicine, China Academy of Chinese Medical Sciences, Beijing 100700, China
³. Qingdao Hiser Hospital, Qingdao 266033, China
⁴. Institute of Acupuncture and Moxibustion, China Academy of Chinese Medical Sciences, Beijing 100700, China
⁵. China Academy of Chinese Medical Sciences, Beijing 100700, China

全文: PDF(286 KB) HTML

Abstract：

Traditional Chinese patent medicines are widely used to treat stroke because it has good efficacy in the clinical environment. However, because of the lack of knowledge on traditional Chinese patent medicines, many Western physicians, who are accountable for the majority of clinical prescriptions for such medicine, are confused with the use of traditional Chinese patent medicines. Therefore, the aid-decision method is critical and necessary to help Western physicians rationally use traditional Chinese patent medicines. In this paper, Manifold Ranking is employed to develop the aid-decision model of traditional Chinese patent medicines for stroke treatment. First, 115 stroke patients from three hospitals are recruited in the cross-sectional survey. Simultaneously, traditional Chinese physicians determine the traditional Chinese patent medicines appropriate for each patient. Second, particular indicators are explored to characterize the population feature of traditional Chinese patent medicines for stroke treatment. Moreover, these particular indicators can be easily obtained by Western physicians and are feasible for widespread clinical application in the future. Third, the aid-decision model of traditional Chinese patent medicines for stroke treatment is constructed based on Manifold Ranking. Experimental results reveal that traditional Chinese patent medicines can be differentiated. Moreover, the proposed model can obtain high accuracy of aid decision.

Key words： traditional Chinese patent medicines stroke aid decision data mining manifold ranking

收稿日期: 2016-09-19 出版日期: 2017-08-29

Corresponding Author(s): Yufeng Zhao,Baoyan Liu

引用本文:

. [J]. Frontiers of Medicine, 2017, 11(3): 432-439.
Yufeng Zhao, Bo Liu, Liyun He, Wenjing Bai, Xueyun Yu, Xinyu Cao, Lin Luo, Peijing Rong, Yuxue Zhao, Guozheng Li, Baoyan Liu. A novel classification method for aid decision of traditional Chinese patent medicines for stroke treatment. Front. Med., 2017, 11(3): 432-439.

链接本文:

https://academic.hep.com.cn/fmd/CN/10.1007/s11684-017-0511-1
https://academic.hep.com.cn/fmd/CN/Y2017/V11/I3/432

Fig.1

Tab.1

Fig.2

Symbols	Definition
$p = {p k i, k = 1, ..., K; i = 1, ..., M}$	Set of patients
$C = {c j, j = 1, ..., N}$	Set of Chinese patent medicine
$W = {w i j, i = 1, ..., M; j = 1, ..., M}$	Set of weight probability

Tab.2

Tab.3

Inputs
Similarity matrix of patients

M s

Initial weight probability matrix

M w

for all medicine classes
Outputs
Final weight probability matrix

M w *

Procedure
Step 1: Collecting the similarity matrix of the patients

M s

Step 2: Normalizing the similarity matrix with Eq. (2)

(2)

M n o r m = M D − 12 M s M D − 12,

where

M D

is a diagonal matrix and

M D i i

is the sum of the

i − t h

row of the weight probability matrix

M w

Step 3: Iterating Eq. (3) until the converged solution

M w *

is achieved

(3)

M w * (t + 1) = α M n o r m M w * (t) + (1 − α) M w (0),

where t is the number of iteration

α ∈ [0, 1]

, and

M w (0)

is the initial weight probability matrix
Step 4: Deciding the initial medicine list of each patient based on the final weight probability matrix

M w *

Tab.4

Tab.5

Fig.3

1	Li S, Ji J. Rational use of Chinese traditional patent medicine. China Mod Med (Zhongguo Dang Dai Yi Yao) 2011; 18(12): 102–104 (in Chinese)
2	Wu J, Hu M, Song M, Wu P, Jiang Y. Catalog proprietary varieties of essential drugs listed by the production distribution. China Pharm (Zhongguo Yao Fang) 2010; 21(24): 2214–2218 (in Chinese)
3	Yang L. Adverse reaction reports and analysis of 416 cases in a region proprietary. Med Hyg (Yi Yao Wei Sheng) 2015; 1(8): 159–159 (in Chinese)
4	Lu L. Chinese traditional patent medicine comparable to antibiotic abuse. Nanfang Daily (Nanfang Ri Bao), August 23, 2011; B01 (in Chinese)
5	Guo C, Huang L. Rational application of proprietary Chinese medicines in the treatment of coronary heart disease. Chin J Integr Med Cardio Cerebrovasc Dis (Zhong Xi Yi Jie He Xin Nao Xue Guan Bing Za Zhi) 2016; 14(18): 2131–2133 (in Chinese)
6	Wu S. Reason of abuse for Chinese Traditional Patent Medicine. Xinhua Daily Teleg (Xin Hua Mei Ri Dian Xun), August 24, 2011; 01 (in Chinese)
7	Wan K. Analysis and unreasonable application of preventive measures in the prescription medicine. Medicine (Yi Yao) 2015; 4(1): 251 (in Chinese)
8	Guan Y, Zhou C, Liu J. Problem analysis of Chinese traditional patent medicine made by Western medicine doctors. Chin J Clin Ration Drug Use (Lin Chuang He Li Yong Yao Za Zhi) 2010; 3(13): 61 (in Chinese)
9	Li G, Yan S, You M, Sun S, Ou A. Intelligent ZHENG classification of hypertension depending on ML-kNN and information fusion. Evid Based Complement Alternat Med 2012; 2012: 837245 https://doi.org/10.1155/2012/837245 pmid: 22701510
10	Zhang X. Application of topic model in the TCM clinic. Doctoral dissertation. Beijing Jiaotong University, 2011 (in Chinese)
11	Zhang R, Zhou X, Yao N. Herb combination relation of liver tune certification based on association rule. Chin J Info Tradit Chin Med (Zhongguo Zhong Yi Yao Xin Xi Za Zhi) 2010; 17(2): 97–99 (in Chinese)
12	Zhou X, Chen S, Liu B, Zhang R, Wang Y, Li P, Guo Y, Zhang H, Gao Z, Yan X. Development of traditional Chinese medicine clinical data warehouse for medical knowledge discovery and decision support. Artif Intell Med 2010; 48(2-3): 139–152 https://doi.org/10.1016/j.artmed.2009.07.012 pmid: 20122820
13	Zhao YF, He LY, Liu BY, Li J, Li FY, Huo RL, Jing XH. Syndrome classification based on manifold ranking for viral hepatitis. Chin J Integr Med 2014; 20(5): 394–399 https://doi.org/10.1007/s11655-013-1659-4 pmid: 24174345
14	Feng Q, Zhou X, Huang H, Yu J, Zhang Y, Tong X, Zhang R, Liu B. A MDP solution for traditional Chinese medicine treatment planning. International Conference of Biomedical Engineering and InformaticsOctober 16–18, 2010, Yantai, China. 2250–2254
15	Feng Q. POMDP approximate solution and in Chinese medicine clinic program optimization. Doctoral dissertation. Beijing Jiaotong University, 2011 (in Chinese)
16	Soni J, Ansari U, Sharma D, Soni S. Predictive data mining for medical diagnosis: an overview of heart disease prediction. Int J Comput Appl 2014; 8(17): 43–48
17	Wu D, Lin J, Wang P, Wang Y, Lu F. Analysis on composition principles of prescriptions for erectile dysfunction by using traditional Chinese medicine inheritance system. Chin Tradit Patent Med (Zhong Cheng Yao) 2016; 38(4): 755–759 (in Chinese)
18	Li Y, Zheng G, Liu L. Treatment rules of Sinomenium acutum by text mining. World Chin Med (Shi Jie Zhong Yi Yao) 2015; 10(6): 823–827 (in Chinese)
19	Peng J, Hu J, Liu B. Clinical aid-decision support system developed based on the network information technology. International Conference of Traditional Chinese Medicine EngineeringDecember 6–8, 2006, Shanghai, China. 134–137 (in Chinese)

Viewed

Full text

Abstract

Cited

Shared

Discussed