A Method for Finding Groups of Related Herbs in Traditional Chinese Medicine

As a complementary system to Western medicine, Traditional Chinese Medicine (TCM) provides a unique theoretical and practical approach of treatment to diseases over thousands of years. Accompanying with the increasing number of TCM digital books in digital library, there is an urgent need to explore these resources by the techniques of knowledge discovery. We present a method for creating a network of herbs and partitioning it into groups of related herbs. The method extracts structured information from several TCM digital books, then a new method named Support and Dependency Evaluation (SDE) is presented for herbal combinational rule mining. The herbal network is created from the extracted dataset of paired herbs. The partitioning procedure is designed to extend FEC algorithm to deal with the weighted herbal network. Experiments demonstrate that the method proposed has the capability of discovering groups of related herbs.

[1]  A. Clauset.  Finding local community structure in networks. , 2005, Physical review. E, Statistical, nonlinear, and soft matter physics.

[2]  M. Newman,et al.  Finding community structure in very large networks. , 2004, Physical review. E, Statistical, nonlinear, and soft matter physics.

[3]  Tao Zhang,et al.  Using Formal Concept Analysis to Visualize Relationships of Syndromes in Traditional Chinese Medicine , 2010, ICMB.

[4]  Javed Mostafa,et al.  Detecting Gene Relations from MEDLINE Abstracts , 2000, Pacific Symposium on Biocomputing.

[5]  Zhaohui Wu,et al.  Integrative mining of traditional Chinese medicine literature and MEDLINE for functional gene networks , 2007, Artif. Intell. Medicine.

[6]  Wei Ren,et al.  Simple probabilistic algorithm for detecting community structure. , 2009, Physical review. E, Statistical, nonlinear, and soft matter physics.

[7]  Jiming Liu,et al.  Community Mining from Signed Social Networks , 2007, IEEE Transactions on Knowledge and Data Engineering.

[8]  Santo Fortunato,et al.  Community detection in graphs , 2009, ArXiv.

[9]  Hongjun Yang,et al.  NEW DRUG R&D OF TRADITIONAL CHINESE MEDICINE: ROLE OF DATA MINING APPROACHES , 2009 .

[10]  Xia Chen,et al.  Automatic symptom name normalization in clinical records of traditional Chinese medicine , 2010, BMC Bioinformatics.

[11]  M E J Newman,et al.  Finding and evaluating community structure in networks. , 2003, Physical review. E, Statistical, nonlinear, and soft matter physics.

[12]  J. Jacobson,et al.  Use of complementary and alternative medicine among United States adults: the influences of personality, coping strategies, and social support. , 2005, Preventive medicine.

[13]  S. Fortunato,et al.  Resolution limit in community detection , 2006, Proceedings of the National Academy of Sciences.

[14]  Zhaohui Wu,et al.  Knowledge discovery in traditional Chinese medicine: State of the art and perspectives , 2006, Artif. Intell. Medicine.

[15]  M. Mitrovic,et al.  Spectral and dynamical properties in classes of sparse networks with mesoscopic inhomogeneities. , 2008, Physical review. E, Statistical, nonlinear, and soft matter physics.

[16]  Juan Mei,et al.  Revealing network communities through modularity maximization by a contraction–dilation method , 2009 .

[17]  Yang Yan,et al.  Msuggest: a semantic recommender framework for traditional chinese medicine book search engine , 2009, CIKM.