Complex Systems Entropy Network and Its Application in Data Mining for Chinese Medicine Tumor Clinics

Abstract

This study was aimed at investigating the method of data mining for complex Chinese medicine tumor clinical data. This article introduces a complex systems entropy network for data mining in tumor clinics. A mutual information algorithm based on the random permutation test was proposed for assessing the correlation of multi-variables, and a complex network was established. Based on the tumor clinical data (718 cases) collected, data mining was performed with the help of the statistical information of the complex network. The results showed that interaction effects among multi-variables were discovered by a complex systems entropy network. A total of 116 pairs of synergy variables and 14 core synergy cliques, 82 pairs of antagonistic variables and 7 core antagonistic cliques were found after 718 cases of data mining. The results, for the most part, correspond with the actual clinics. It was concluded that the complex systems entropy network is suitable for the analysis of interaction effects among multi-variables and also for data mining in complex Chinese medicine clinics.