Mining the associations between pharmic quality and ingredients of traditional Chinese medicines

Abstract

This paper presents our works to tackle three key problems in modern research of traditional Chinese medicines. Based on a dataset of 100 medicines (each with 60 major ingredients), we evaluate various data mining approaches in order to unveil the underlying associations between these chemical ingredients and the pharmic qualities of the medicines. Based on our experiements, we conclude that these associations do exist and can be effectively unveiled. Various performance enhancement techniques are then evaluated, among which we identify the best classification approach for practice. These unveiled associations between pharmic quality and ingredients of traditional Chinese medicine can help guide future researches in this area, particularly in the development of new medicines.