Title :
The application characteristics of traditional Chinese medical science treatment on headache based on data-mining Apriori algorithm
Author :
Miao Wang ; Lei Zhang ; Zihao Zhang ; Chen Xu ; Guobin Chen ; Huiliang Shang ; Xujun Li
Author_Institution :
Res. Lab. for Constr. & Applic. of Stand. in Med. Inf., Shanghai Univ. of T.C.M., Shanghai, China
Abstract :
As the mechanism of the effective traditional Chinese medical science treatment remains confounding, researchers seek to analyze the therapies using traditional Chinese medicine (TCM) with advanced techniques. In this paper we take advantage of the technique of data mining with the software SPSS (Statistical Product and Service Solutions), in particular the Apriori algorithm for association rules mining (ARM), which discovers the following relationship by iteratively analyzing large datasets of TCM medical records. After analyzing the database, we are likely to reveal the mysterious interrelationships among TCM syndromes, clinical symptoms and curative Chinese herbal medicine. Here we list the principals, steps and pseudo-codes of Apriori algorithm, and then apply Apriori algorithm to analyze Chinese traditional medical cases of headache. Through verification, the Apriori algorithm proves effective in helping traditional Chinese doctors decide what to prescribe when facing various patients with headache. Finally we offer some improvement of Apriori algorithm for ARM to boom its effectiveness.
Keywords :
data mining; diseases; drugs; medical computing; patient treatment; Apriori algorithm; Statistical Product and Service Solutions software; association rules mining; curative Chinese herbal medicine; data-mining; headache; traditional Chinese doctors; traditional Chinese medical science treatment; traditional Chinese medicine; Algorithm design and analysis; Association rules; Itemsets; Medical diagnostic imaging; Tongue; Apriori; Traditional Chinese Medical; data mining; headache;
Conference_Titel :
Bioinformatics and Biomedicine (BIBM), 2014 IEEE International Conference on
Conference_Location :
Belfast
DOI :
10.1109/BIBM.2014.6999346