Skip to main content
SpringerLink
Log in

Selecting an appropriate interestingness measure to evaluate the correlation between Chinese medicine syndrome elements and symptoms

  • Feature Article
  • Published:
Chinese Journal of Integrative Medicine Aims and scope Submit manuscript

Abstract

To select the best interestingness measure appropriate for evaluating the correlation between Chinese medicine (CM) syndrome elements and symptoms, 60 objective interestingness measures were selected from different subjects. Firstly, a hypothesis for a good measure was proposed. Based on the hypothesis, an experiment was designed to evaluate the measures. The experiment was based on the clinical record database of past dynasties including 51 186 clinical cases. The selected data set in this study had 44 600 records. Cold and heat were selected as the experimental CM syndrome elements. Three indicators calculated according to the distances between two CM syndrome elements were obtained in the experiment and combined into one indicator. The Z score, ϕ-coefficient, and Kappa were selected from 60 measures after the experiment. The Z score and ϕ-coefficient were selected according to subjective interestingness. Finally, the ϕ-coefficient was selected as the best measure for its low computational complexity. The method introduced in this paper may be used in other similar territories.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. Zhu W. Standardization research of differentiation system of symptoms and signs and “syndrome” in TCM. Tianjin J Tradit Chin Med (Chin) 2002;19:1–3.

    Google Scholar 

  2. Wang Y, Zhang Q, Zhang Z. Extraction of syndrome elements and destination. J Shandong Univ Chin Med (Chin) 2006;30:6–7.

    CAS  Google Scholar 

  3. Sun Z, Xi G, Yi J, Zhao D. Select informative symptoms combination for diagnosing syndrome. J Biol Syst 2007;15:27–38.

    Article  Google Scholar 

  4. Wang J, Chu F, Li J, Yao K, Zhong J, Zhou K, et al. Study on syndrome element characteristics and its correlation with coronary angiography in 324 patients with coronary heart disease. Chin J Integr Med 2008;14:274–280.

    Article  PubMed  CAS  Google Scholar 

  5. Tan S, Tillisch K, Bolus S, Olivas T, Spiegel B, Naliboff B, et al. Traditional Chinese medicine based subgrouping of irritable bowel syndrome patients. Am J Chin Med 2005;33:365–379.

    Article  PubMed  CAS  Google Scholar 

  6. Agrawal R, Imielinski T, Swami A. Mining association rules between sets of items in large databases. ACM SIGMOD Record 1993;22:207–216.

    Article  Google Scholar 

  7. Brijs T, Vanhoof K, Wets G. Defining interestingness for association rules. Intern J Inf Theory Applic 2003;10:370–376.

    Google Scholar 

  8. Brin S, Motwani R, Silverstein C. Beyond market baskets: generalizing association rules to correlations. ACM SIGMOD Record 1997;26:265–276

    Article  Google Scholar 

  9. McGarry K. A survey of interestingness measures for knowledge discovery. Knowl Eng Rev 2005;20:39–61.

    Article  Google Scholar 

  10. Tan P, Kumar V, Srivastava J. Selecting the right objective measure for association analysis. Inf Syst 2004;29:293–313.

    Article  Google Scholar 

  11. Luo K, Wu J. Evaluating criterion of association rules. Control Decision 2003;18:277–280.

    Google Scholar 

  12. Yi W, Wei J, Wang M. Mining efficient association rules. Computr Eng Sci 2005;27:91–94.

    Google Scholar 

  13. Chen J, Gao Y. Evaluating criterion of association rules using efficiency. Comput Eng Applic 2009;45:141–142.

    Google Scholar 

  14. Huang Y, ed. Clinical epidemiology. Beijing: People’s Medical Publishing House; 2006:144–155.

    Google Scholar 

  15. Pecina P. A machine learning approach to multiword expression extraction. Towards a shared task for Multiword Expressions (MWE 2008), 2008:54–57.

    Google Scholar 

  16. Zhou X, Liu B, Wu Z, Feng Y. Integrative mining of traditional Chinese medicine literature and MEDLINE for functional gene networks. Artif Intel Med 2007;41:87–104.

    Article  Google Scholar 

  17. Piatetsky-Shapiro G. Discovery, analysis, and presentation of strong rules. Knowledge Discov Databases 1991:229–248.

  18. Lenca P, Meyer P, Vaillant B, Lallich S. A multicriteria decision aid for interestingness measure selection. Department LUSSI, ENST Bretagne, Technical Report LUSSI-TR-2004-01-EN 2004.

  19. Geng L, Hamilton H. Interestingness measures for data mining: a survey. ACM Comput Surv (CSUR) 2006;38:9.

    Article  Google Scholar 

  20. Zhang Q, Wang Y, Zhang Z, Zhang Q, Song G. The establishment and statistics on the clinical records database of the past dynasties. J Shandong Univ Chin Med (Chin) 2005;29:298–299.

    Google Scholar 

  21. Zhang Q, Wang Y, Zhang L, Yu D, Wang Y. Independent symptoms with the least intension. J Beijing Univ Tradit Chin Med (Chin) 2010:5–10.

  22. Han J, Kamber M, eds. Data mining: concepts and techniques. 2nd ed. The morgan kaufmann series in data management systems. San Francisco: Morgan Kaufmann Publishers; 2006:388.

Download references

Author information

Authors and Affiliations

  1. Beijing Jiaotong University, Beijing, 100044, China

    Lei Zhang  (张 磊) & Dong-lin Yu  (于东林)

  2. Institute of Basic Research in Clinical Medicine, China Academy of Chinese Medical Sciences, Beijing, 100700, China

    Yi-guo Wang  (王义国) & Qi-ming Zhang  (张启明)

Authors
  1. Lei Zhang  (张 磊)
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Dong-lin Yu  (于东林)
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yi-guo Wang  (王义国)
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Qi-ming Zhang  (张启明)
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Lei Zhang  (张 磊).

Additional information

Supported by National Natural Science Fundation of China (No. 30772695, No. 81001500); 11th Five-Year National Science Support Project of China (No. 2006BAI08B01-05); National Science and Technology Major Projects (No. 2009ZX10005-019)

Rights and permissions

Reprints and permissions

About this article

Cite this article

Zhang, L., Yu, Dl., Wang, Yg. et al. Selecting an appropriate interestingness measure to evaluate the correlation between Chinese medicine syndrome elements and symptoms. Chin. J. Integr. Med. 18, 93–99 (2012). https://doi.org/10.1007/s11655-011-0859-z

Download citation

  • Received:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11655-011-0859-z

Keywords

Search

Navigation