Author_Institution :
Dept. of Chinese Med., Guangdong Women & Children Hosp., Guangzhou, China
Abstract :
Objective: To analyze the component law of Chinese medicines for gout, and develop new prescriptions for gout through unsupervised data mining methods. Methods: Chinese medicine recipes for gout were collected and recorded in the database, and then the correlation coefficient between herbs, core combinations of herbs and new prescriptions were analyzed by using modified mutual information, complex system entropy cluster and unsupervised hierarchical clustering, respectively. Results: Based on the analysis of 70 Chinese medicine recipes for gout, 22 drugs with high-frequency occurrence in these recipes, 26 frequently-used herb pairs and 5 core combinations were founded, and 3 new recipes for gout were developed. Conclusion: Chinese medicines for gout were mainly consist of blood-activating and stasis-dispelling medicinal, dampness-resolving medicinal, spleen fortifying and dampness draining medicinal, wind-dampness dispelling and heat clearing medicinal. The the treatment principle for gout is to eliminate the pathogenic factors. Radix Clematidis, Rhizoma Atractylodis, Rhizoma Dioscoreae Septemlobae, Semen Coicis, Cortex Phellodendri, Rhizoma Alismatis, Rhizoma Anemarrhenae, Radix Achyranthis Bidentatae, Radix Glycyrrhizae, Poria, Semen Plantaginis, and Rhizoma Atractylodis Macrocephalae are the main herbal drugs used in the treatment of gout.
Keywords :
biological organs; blood; data mining; diseases; drugs; entropy; medical information systems; patient treatment; unsupervised learning; Chinese medicine component law analysis; Chinese medicine recipe analysis; blood-activating medicinal component; complex system entropy cluster; correlation coefficient; cortex phellodendri; dampness draining medicinal component; dampness-resolving medicinal component; gout treatment; heat clearing medicinal component; herb core combinations; herbal drugs; modified mutual information; pathogenic factors; poria; radix achyranthis bidentatae; radix clematidis; radix glycyrrhizae; rhizoma alismatis; rhizoma anemarrhenae; rhizoma atractylodis macrocephalae; rhizoma dioscoreae septemlobae; semen coicis; semen plantaginis; spleen fortifying medicinal component; stasis-dispelling medicinal component; unsupervised data mining methods; unsupervised hierarchical clustering; wind-dampness dispelling medicinal component; Data mining; Databases; Drugs; Entropy; Medical diagnostic imaging; Mutual information; Chinese medicine; gout; new prescription discovery; unsupervised data mining methods;
