DocumentCode :
3195843
Title :
Exploring Li-Fa-Fang-Yao rules of major depressive disorder in traditional Chinese medicine through text mining
Author :
Junping Zhan ; Guang Zheng ; Mengmeng Song ; Tong Wei ; Miao Jiang ; Cheng Lu ; Aiping Lu
Author_Institution :
Second affiliated Hosp. of Henan, Univ. of traditional Chinese Med., Zhengzhou, China
fYear :
2013
fDate :
18-21 Dec. 2013
Firstpage :
460
Lastpage :
464
Abstract :
In traditional Chinese medicine, rules of Li-Fa-Fang-Yao is of critical importance in clinical practices. Li-Fa-Fang-Yao, which means principles, methods, formulae, and Chinese herbal medicines respectively, indicate the four basic steps of diagnosis and treatment: determining the cause, mechanism and location of the disease according to the medical theories and principles, then deciding the treatment principle and method, and finally selecting a formula as well as proper Chinese herbal medicines. In this paper, focused on major depressive disorder, we explored the rules of Li-Fa-Fang-Yao within the framework of traditional Chinese medicine. Through calculation, three clusters of Li-Fa-Fang-Yao on major depressive disorder were found based on the syndrome differentiation. What´s more, these three clusters can also be validated by textbooks of traditional Chinese medicine.
Keywords :
data mining; diseases; medical diagnostic computing; medical disorders; patient diagnosis; patient treatment; text analysis; Chinese herbal medicines; Li-Fa-Fang-Yao rules; depressive disorder; disease diagnosis; disease treatment; medical theory; syndrome differentiation; text mining; traditional Chinese medicine textbook; Conferences; Diseases; Educational institutions; Liver; Medical diagnostic imaging; Mood; Text mining; Li-Fa-Fang-Yao; depression; text mining; traditional Chinese medicine; validation;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Bioinformatics and Biomedicine (BIBM), 2013 IEEE International Conference on
Conference_Location :
Shanghai
Type :
conf
DOI :
10.1109/BIBM.2013.6732536
Filename :
6732536
Link To Document :
بازگشت