Syndrome differentiation is an important topic in traditional Chinese medicine (TCM). Decision tree, one of the data mining algorithms developed, is a method to induce rules from data. In this paper, decision tree is applied to extract syndrome differentiation rules from 293 cases related to liver and kidney yin deficiency, damp-heat smoldering and Stasis and heat smoldering syndrome. Thus the decision tree classification model is obtained and some important factors are selected to three mainly syndromes of posthepatitic cirrhosis; corresponding syndrome differentiation rules are induced from the model. The classification accuracies are 79.86%, 80.5% and 82% respectively. The experiment results show that the decision method is likely a promising method to extract diagnostic rules from patient records of Chinese medicine and could be expected to be useful in the practice of traditional Chinese medicine.
展开▼