An intelligent drug matching method for traditional Chinese medicine

Chinese medicine prescription, being one of the mainstream medical method in traditional Chinese medicine, always contains complex complicated relationship between drugs which are hard to extract manually. However, with the rise of data-mining technology, it is more possible to finish such tasks intelligently with large scale text data. In order to discover the relationship between drugs, the relevance of prescription as well as attributes of drugs were quantified to establish the network model, then the state-of-art technologies in graph mining were utilized to study the matching rules of drugs in a specific prescription. Experiment results shows that our method could simulate results that are similar with the theoretical ones in traditional Chinese medicine and could be regarded as potential approach for automatic drug matching.

[1]  M E J Newman,et al.  Fast algorithm for detecting community structure in networks. , 2003, Physical review. E, Statistical, nonlinear, and soft matter physics.

[2]  C Q Hu,et al.  Effect of "Si Jun Zi (four gentlemen) Tang" decoction on monoamine transmitter in brain of reserpinized mice. , 1983, Journal of traditional Chinese medicine = Chung i tsa chih ying wen pan.

[3]  Mohammad Fraiwan Al-Saleh,et al.  On the Similarity Structure of Order Statistics , 2007 .

[4]  G. I. Ivchenko,et al.  On the jaccard similarity test , 1998 .

[5]  Korris Fu-Lai Chung,et al.  Transfer affinity propagation-based clustering , 2016, Inf. Sci..

[6]  Elena Rubei,et al.  On the weights of simple paths in weighted complete graphs , 2012, 1210.0845.

[7]  Delbert Dueck,et al.  Clustering by Passing Messages Between Data Points , 2007, Science.

[8]  M. Ramanathan,et al.  Network‐Based Approaches in Drug Discovery and Early Development , 2013, Clinical pharmacology and therapeutics.

[9]  Alain Bretto,et al.  Random walks in directed hypergraphs and application to semi-supervised image segmentation , 2014, Comput. Vis. Image Underst..

[10]  Shaowu Zhang,et al.  A general method of community detection by identifying community centers with affinity propagation , 2016 .

[11]  Chang-Dong Wang,et al.  Chinese-Tibetan bilingual clustering based on random walk , 2015, Neurocomputing.

[12]  Yingshan Zhang,et al.  Mathematical Reasoning of Treatment Principle Based on “Yin Yang Wu Xing” Theory in Traditional Chinese Medicine , 2011 .

[13]  Xianjun Fu,et al.  Study of the distribution patterns of the constituent herbs in classical Chinese medicine prescriptions treating respiratory disease by data mining methods , 2013, Chinese Journal of Integrative Medicine.

[14]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Jiliang Cao,et al.  Compatibility art of traditional Chinese medicine: from the perspective of herb pairs. , 2012, Journal of ethnopharmacology.

[16]  Jane Labadin,et al.  Feature selection based on mutual information , 2015, 2015 9th International Conference on IT in Asia (CITA).

[17]  Jiawei Han,et al.  Frequent pattern mining: current status and future directions , 2007, Data Mining and Knowledge Discovery.

[18]  Y G Yu,et al.  [A theory on Chinese drugs and their system structure]. , 1989, Zhongguo Zhong yao za zhi = Zhongguo zhongyao zazhi = China journal of Chinese materia medica.