Please wait a minute...
Frontiers of Medicine

ISSN 2095-0217

ISSN 2095-0225(Online)

CN 11-5983/R

Postal Subscription Code 80-967

2018 Impact Factor: 1.847

Front. Med.    2018, Vol. 12 Issue (2) : 206-217    https://doi.org/10.1007/s11684-017-0525-8
RESEARCH ARTICLE |
Multistage analysis method for detection of effective herb prescription from clinical data
Kuo Yang1, Runshun Zhang2, Liyun He3, Yubing Li1, Wenwen Liu1, Changhe Yu3, Yanhong Zhang3, Xinlong Li3, Yan Liu4, Weiming Xu5, Xuezhong Zhou1,4(), Baoyan Liu4()
1. School of Computer and Information Technology and Beijing Key Lab of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing 100044, China
2. Guanganmen Hospital, China Academy of Chinese Medical Sciences, Beijing 100053, China
3. Institute of Basic Clinical Medicine, China Academy of Chinese Medical Sciences, Beijing 100700, China
4. Data Center of Traditional Chinese Medicine, China Academy of Chinese Medical Sciences, Beijing 100700, China
5. Institute of Basic Theory of Traditional Chinese Medicine, China Academy of Chinese Medical Sciences, Beijing 100700, China
 Download: PDF(432 KB)   HTML
 Export: BibTeX | EndNote | Reference Manager | ProCite | RefWorks
Abstract

Determining effective traditional Chinese medicine (TCM) treatments for specific disease conditions or particular patient groups is a difficult issue that necessitates investigation because of the complicated personalized manifestations in real-world patients and the individualized combination therapies prescribed in clinical settings. In this study, a multistage analysis method that integrates propensity case matching, complex network analysis, and herb set enrichment analysis was proposed to identify effective herb prescriptions for particular diseases (e.g., insomnia). First, propensity case matching was applied to match clinical cases. Then, core network extraction and herb set enrichment were combined to detect core effective herb prescriptions. Effectiveness-based mutual information was used to detect strong herb–symptom relationships. This method was applied on a TCM clinical data set with 955 patients collected from well-designed observational studies. Results revealed that groups of herb prescriptions with higher effectiveness rates (76.9% vs. 42.8% for matched samples; 94.2% vs. 84.9% for all samples) compared with the original prescriptions were found. Particular patient groups with symptom manifestations were also identified to help investigate the indications of the effective herb prescriptions.

Keywords effective prescription detection      herb set enrichment analysis      core network extraction      insomnia      personalized treatment     
Corresponding Authors: Xuezhong Zhou,Baoyan Liu   
Just Accepted Date: 03 May 2017   Online First Date: 23 June 2017    Issue Date: 02 April 2018
 Cite this article:   
Kuo Yang,Runshun Zhang,Liyun He, et al. Multistage analysis method for detection of effective herb prescription from clinical data[J]. Front. Med., 2018, 12(2): 206-217.
 URL:  
http://academic.hep.com.cn/fmd/EN/10.1007/s11684-017-0525-8
http://academic.hep.com.cn/fmd/EN/Y2018/V12/I2/206
Fig.1  Multistage analysis method to identify effective herb prescriptions by integrating propensity case matching, complex network analysis, and herb set enrichment analysis.
Data set Number
Total sample 955
Effective sample 842
Ineffective sample 113
Total visits 2049
Herbs 536
Symptoms 1128
Syndromes 250
Tab.1  Clinical data of insomnia cases
Frequency of symptoms Number of symptoms Number of matched cases
≥5 216 42
≥10 138 77
≥40 53 87
≥100 24 102
≥170 10 107
Tab.2  Propensity case matching comparison
Symptoms Frequency Proportion
Difficulty falling asleep 399 41.78%
Dreaminess 346 36.23%
Fine pulse 258 27.02%
Dizzy 253 26.49%
Vexation 234 24.50%
Ease of waking up 229 23.98%
Poor appetite 222 23.20%
Asthenia 209 21.88%
Palpitation 183 19.16%
Poor spiritual fitness 170 17.80%
Tab.3  Frequency of the top 10 symptoms
Fig.2  Distribution of propensity scores. (A) Propensity score distribution of all effective and ineffective cases. The scores of all samples distributed between 0 and 0.5. For effectiveness samples, 78% of propensity scores were below 0.15. (B) Propensity score distribution of effectiveness and control cases matched. Matched cases yielded relatively good results.
Fig.3  Distribution of herbs and symptoms in the 214 cases. (A) Frequencies of herbs in effective and ineffective cases. Effective and ineffective samples comprised 269 and 273 herbs respectively. (B) Frequencies of symptoms in the 214 cases.
Herb Effective prescriptions Ineffective prescriptions P-value
Rank Frequency Rank Frequency
Semen Ziziphi Spinosae 1 96 (47%) 3 118 (43%) 0.4015
Radix Paeoniae Alba 2 75 (37%) 2 120 (44%) 0.1122
Radix Angelicae Sinensis 3 73 (36%) 1 138 (51%) 0.0012
Polygala tenuifolia Willd 4 69 (34%) 8 78 (29%) 0.2174
Poria with Hostwood 5 64 (32%) 13 62 (23%) 0.0333
Radix Glycyrrhizae 6 63 (31%) 4 109 (40%) 0.0410
Ligusticum Wallichii 7 63 (31%) 7 100 (37%) 0.1888
Poria Cocos 8 62 (30%) 6 101 (38%) 0.1310
Rhizoma Acori Tatarinowii 9 54 (26%) 17 56 (21%) 0.1255
Caulis Polygoni Multiflori 10 51 (25%) 32 35 (13%) 0.0006
Radix Bupleuri 16 43 (21%) 5 102 (38%) 0.0001
Coptis Chinensis 15 45 (22%) 9 76 (28%) 0.1502
Fossil Fragments 18 41 (20%) 10 71 (26%) 0.1312
Tab.4  Comparison of the frequency of the top 10 herbs between effective and ineffective prescriptions
Feature Value of feature Frequency P value
Gender Female 138 0.2349
Age (year) 10–20 4 0.5829
21–30 34 0.0531
31–40 57 0.3352
41–50 46 0.1390
51–60 45 1
61–70 17 0.1885
71–80 11 0.2904
Syndrome Blood-stasis syndrome 41 3.68E–08
Blood deficiency 41 1.85E–07
Kidney weakness 25 4.12E–06
Qi deficiency 21 6.24E–05
Restlessness 11 7.11E–05
Liver depression 52 0.0002
Liver prosperous 13 0.0002
Spleen deficiency 21 0.0014
Phlegm heat disturbance 6 0.0032
Tab.5  Bernoulli test results for gender, age, and syndrome
Fig.4  (A) Gender distribution of 214 samples. (B) Age distribution of 214 samples. (C) Top 20 syndromes of highest frequency.
Fig.5  (A) C1network. (B) C2network. The weight represents the frequency that the two herbs appeared in the same prescription. The colors represent herb properties. Brown represents tonic drug, pink represents dissipating blood-stasis drug, green represents sedative drug, bluish-violet represents damp-clearing drug, and red represents heat-clearing drug. The top three herb compatibilities of C 1 were Semen Zizyphi Spinosae–Polygala tenuifolia Willd, Radix Angelicae Sinensis–Radix Paeoniae Alba, and Semen Zizyphi Spinosae–Poria Cocos. The top three herb compatibilities of C2 were Semen Zizyphi Spinosae–Radix Angelicae Sinensis, Polygala tenuifolia Willd–Radix Angelicae Sinensis, and Semen Zizyphi Spinosae–Poria with Hostwood.
Rank Prescription ID Number of herbs P value
1 630 12 <0.0001
2 12525 11 0.0011
3 230554 17 0.0020
4 230555 14 0.0021
5 736 15 0.0081
6 229795 12 0.0083
7 229796 12 0.0083
8 229797 12 0.0083
9 230311 12 0.0083
10 230563 12 0.0083
29 C 1 8 0.0398
Tab.6  HSEA results of the top 10 prescriptions and C 1
Prescription Matched 214 samples Total 955 samples
Effectiveness
/total prescriptions
Effective ratio Effectiveness
/total prescriptions
Effective ratio
C 1 17/63 27.0% 102/156 65.4%
C 2 16/28 57.1% 85/99 85.9%
P 630 10/13 76.9% 49/52 94.2%
P All 201/470 42.8% 1,739/2,049 84.9%
Tab.7  Comparison of effectiveness ratios of different herb prescriptions
Fig.6  EMI distribution of herb–symptom relationships. A total 80% of the EMIs of herb–symptom relationships were between 0 and 0.01. The strongest herb–symptom relationship was that of Rhizoma Atractylodis Macrocephalae–asthenia.
Rank Herb Symptom EMI
1 Rhizoma Atractylodis Macrocephalae Asthenia 0.1358
2 Codonopsis Pilosula Abdominaldistension 0.1189
3 Radix Glehniae Tooth markon tongue 0.0980
4 Sophora
Flavescens
Nervous 0.0964
5 Radix sileris Bulgy tongue 0.0922
6 Rhizoma Pinelliae Difficulty sleeping after waking 0.0902
7 BombyxBatryticatus Nervous 0.0832
8 Longan meat Dry eye 0.0796
9 Radix Paeoniae Rubra Mild menstruation 0.0782
10 Rhizoma Pinelliae Wake up fatigue 0.0764
Tab.8  EMIs of the top 10 herb–symptom relationships
Rank Symptom Rank Symptom
1 Dry eye 11 Palpitation
2 Watery stool 12 Pale complexion
3 Abdominaldistension 13 Loose stools
4 Weak pulse 14 White fur
5 Asthenia 15 Poor appetite
6 Rapid andweak pulse 16 Frequent passing of stool
7 Tooth markon tongue 17 Yellow facial skin
8 Weak body 18 Yellow skin color
9 Fatigued limbs 19 Yellow skin
10 Thin lingual fur 20 Pale tongue
Tab.9  Top 20 symptoms detected forP630
1 Hu J, Liu B. The basic theory, diagnostic, and therapeutic system of traditional Chinese medicine and the challenges they bring to statistics. Stat Med 2012; 31(7): 602–605
https://doi.org/10.1002/sim.4409 pmid: 22238066
2 Lu AP, Jia HW, Xiao C, Lu QP. Theory of traditional Chinese medicine and therapeutic method of diseases. World J Gastroenterol 2004; 10(13): 1854–1856
https://doi.org/10.3748/wjg.v10.i13.1854 pmid: 15222022
3 Zhou X, Peng Y, Liu B. Text mining for traditional Chinese medical knowledge discovery: a survey. J Biomed Inform 2010; 43(4): 650–660
https://doi.org/10.1016/j.jbi.2010.01.002 pmid: 20074663
4 Yan S, Zhang R, Zhou X, Li P, He L, Liu B. Exploring effective core drug patterns in primary insomnia treatment with Chinese herbal medicine: study protocol for a randomized controlled trial. Trials 2013; 14(1): 1–7
https://doi.org/10.1186/1745-6215-14-61 pmid: 23448313
5 Yang K, Zhou XZ, Zhang RS, Liu BY, Lei L, Zhang XP, Chu HW, Sun CK, Gao ZY, Xu H. Integrating herb effect similarity for network-based herb target prediction. International Conference on Biomedical Engineering and Informatics. 2015, 483–488
6 Du NL, Zhou XZ, Zhang RS, Jia CY, Yu J, Liu BY. Multiscale backbone based network comparison algorithm for effective herbal interaction analysis. International Conference on Biomedical Engineering and Informatics. 2011, 1757–1762
7 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
8 Zhang NL, Yuan S, Chen T, Wang Y. Latent tree models and diagnosis in traditional Chinese medicine. Artif Intell Med 2008; 42(3): 229–245
https://doi.org/10.1016/j.artmed.2007.10.004 pmid: 18096374
9 Zhou XZ, Zhang RS, Shah J, Rajgor D, Wang YH, Pietrobon R, Liu BY, Chen J, Zhu JG, Gao RL. Patterns of herbal combination for the treatment of insomnia commonly employed by highly experienced Chinese medicine physicians. Chin J Integr Med 2011; 17(9): 655–662
https://doi.org/10.1007/s11655-011-0841-9 pmid: 21910065
10 Chen T, Zhou XZ, Zhang RS, Zhang LW. Discovery of regularities in the use of herbs in Chinese medicine prescriptions. Chin J Integr Med 2012; 18(2): 88–92
https://doi.org/10.1007/s11655-011-0860-6 pmid: 21994029
11 Poon SK, Poon J, McGrane M, Zhou X, Kwan P, Zhang R, Liu B, Gao J, Loy C, Chan K, Sze DMY. A novel approach in discovering significant interactions from TCM patient prescription data. Int J Data Min Bioinform 2011; 5(4): 353–368
https://doi.org/10.1504/IJDMB.2011.041553 pmid: 21954669
12 Chen YL, Lee CY, Huang KH, Kuan YH, Chen M. Prescription patterns of Chinese herbal products for patients with sleep disorder and major depressive disorder in Taiwan. J Ethnopharmacol 2015; 171: 307–316
https://doi.org/10.1016/j.jep.2015.05.045 pmid: 26068429
13 Cao J. The common prescription patterns based on the hierarchical clustering of herb-pairs efficacies. Evid Based Complement Alternat Med 2016; 2016: 6373270
https://doi.org/10.1155/2016/6373270 pmid: 27190534
14 Poon J, Poon S, Yin D, Chan K. Studying herb-herb interaction for insomnia through the theory of complementarities. IEEE International Conference on Bioinformatics and Biomedicine Workshops. IEEE. 2010,722–726
15 Chen H, Poon J, Poon SK, Cui L, Fan K, Sze D. Ensemble learning for prediction of the bioactivity capacity of herbal medicines from chromatographic fingerprints. BMC Bioinformatics 2015; 16(Suppl 12): 1–8
https://doi.org/10.1186/1471-2105-16-S12-S4 pmid: 26329995
16 Chen JP, Poon J, Poon SK, Xu L, Sze, DMY. Mining symptom-herb patterns from patient records using tripartite graph. Evid Based Complement Alternat Med 2015; 2015:435085
https://doi.org/10.1155/2015/435085
17 D’Agostino RB Jr. Tutorial in biostatistics: propensity score methods for bias reduction in the comparison of a treatment to a non-randomized control group. Stat Med 1998; 17(19): 2265– 2281
https://doi.org/10.1002/(SICI)1097-0258(19981015)17:19<2265::AID-SIM918>3.0.CO;2-B pmid: 9802183
18 Zhou XZ, Zhang XP. Extraction of hierarchical core structures from traditional Chinese medicine herb combination network. Proceedings of 2008 International Conference on Advanced Intelligence. 2008, 262–267
19 Subramanian A, Tamayo P, Mootha VK, Mukherjee S, Ebert BL, Gillette MA, Paulovich A, Pomeroy SL, Golub TR, Lander ES, Mesirov JPA. Gene set enrichment analysis: a knowledge-based approach for interpreting genome-wide expression profiles. Proc Natl Acad Sci USA 2005; 102(43): 15545–15550
https://doi.org/10.1073/pnas.0506580102 pmid: 16199517
20 Merico D, Isserlin R, Stueker O, Emili A, Bader GD. Enrichment map: a network-based method for gene-set enrichment visualization and interpretation. PLoS One 2010; 5(11): e13984
https://doi.org/10.1371/journal.pone.0013984 pmid: 21085593
21 Yeung WF, Chung KF, Man-Ki Poon M, Yan-Yee Ho F, Zhang SP, Zhang ZJ, Tat-Chi Ziea E, Wong VT. Chinese herbal medicine for insomnia: a systematic review of randomized controlled trials. Sleep Med Rev 2012; 16(6): 497–507
https://doi.org/10.1016/j.smrv.2011.12.005 pmid: 22440393
22 Ollivier H, Zurek WH. Quantum discord: a measure of the quantumness of correlations. Phys Rev Lett 2002; 88(1): 017901
https://doi.org/10.1103/PhysRevLett.88.017901 pmid: 11800986
23 Bandyopadhyay U, Biswas A. An alternative test on bernoulli success probability. Sankhyā: Indian Journal of Statistics, Series A(1961–2002) 2000; 62(1): 40–48
24 Wing YK. Herbal treatment of insomnia. Hong Kong Med J 2001; 7(4): 392–402
pmid: 11773674
25 Zhou X, Menche J, Barabási AL, Sharma A. Human symptoms-disease network. Nat Commun 2014; 5: 4212
https://doi.org/10.1038/ncomms5212 pmid: 24967666
26 Liu B, Zhou X, Wang Y, Hu J, He L, Zhang R, Chen S, Guo Y. Data processing and analysis in real-world traditional Chinese medicine clinical data: challenges and approaches. Stat Med 2012; 31(7): 653–660
https://doi.org/10.1002/sim.4417 pmid: 22161304
27 Jiang L, Liu B, Xie Q, Yang S, He L, Zhang R, Yan S, Zhou X, Liu J. Investigation into the influence of physician for treatment based on syndrome differentiation. Evid Based Complement Alternat Med 2013; 2013: 587234
https://doi.org/10.1155/2013/587234 pmid: 24288563
28 Li YB, Zhou XZ, Zhang RS, Wang YH, Peng Y, Hu JQ, Xie Q, Xue YX, Xu LL, Liu XF, Liu BY. Detection of herb-symptom associations from traditional Chinese medicine clinical data. Evid Based Complement Alternat Med 2015; 2015: 1–11
pmid: 25650023
29 Afendi FM, Ono N, Nakamura Y, Nakamura K, Darusman LK, Kibinge N, Morita AH, Tanaka K, Horai H, Altaf-Ul-Amin M, Kanaya S. Data mining methods for omics and knowledge of crude medicinal plants toward big data biology. Comput Struct Biotechnol J 2013; 4(5): 1–14
https://doi.org/10.5936/csbj.201301010 pmid: 24688691
30 Afendi FM, Darusman LK, Hirai A, Altaf-UI-Amin M, Takahashi H, Nakamura K, Kanaya S. System biology approach for elucidating the relationship between Indonesian herbal plants and the efficacy of Jamu. Data Mining Workshops (ICDMW). 2010 IEEE International Conference on IEEE. 2010, 661–668
31 Liu YC, Lei SQ. The Basic Theory of Traditional Chinese Medicine. Beijing: Academy Press, 2005
32 Li ZG, Pan SL. Comparative study on WHO Western Pacific Region and World Federation of Chinese Medicine Societies international standard terminologies on traditional medicine: an analysis of the Five Sensory Organs. J Chin Integr Med (Zhong Xi Yi Jie He Xue Bao) 2009; 7(2): 183–186 (in Chinese)
https://doi.org/10.3736/jcim20090218 pmid: 19216866
[1] Yan Ma, Albert C. Yang, Ying Duan, Ming Dong, Albert S. Yeung. Quality and readability of online information resources on insomnia[J]. Front. Med., 2017, 11(3): 423-431.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed