Objective: To analyze the component law of Chinese patent medicines for anti-influenza and develop new prescriptions for anti-influenza by unsupervised data mining methods.
Methods: Chinese patent medicine recipes for anti-influenza 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 analysis of 126 Chinese patent medicine recipes, the frequency of each herb occurrence in these recipes, 54 frequently-used herb pairs, 34 core combinations were determined, and 4 new recipes for influenza were developed.
Conclusion: Unsupervised data mining methods are able to mine the component law quickly and develop new prescriptions.