基于贝叶斯网络的中医辨证系统

Syndrome Differentiation System of Traditional Chinese Medicine Based on Bayesian Network

将贝叶斯网络运用于中医辨证系统的研究,以更加量化中医辨证诊断系统.通过将中医体系中的916个证候,51项证素及其构成的1700条证名构成中医辨证贝叶斯网络的节点集,初步建立起中医辨证数据库并通过网络学习,形成中医辨证贝叶斯网络结构及概率表.利用建立的贝叶斯网络中医辨证系统,进行数据计量分析、推理验证证候—证素—证名间的关系,其结果与中医专家经验有很高的吻合性,尽管其仍未能全面反映中医辨证的思维能力.所以贝叶斯网络是对中医辨证进行信息挖掘处理的一种较好方法,可应用于中医人工智能辨证系统的建立.

This paper applied Bayesian network to the syndrome differentiation research to improve the quantification of syndrome differentiation diagnosis system in traditional Chinese medicine （TCM）. 916 syndromes, 51 key pattern elements and 1700 syndrome names as nodes collection of Bayesian network were selected for the database, and the framework and probability table for the Bayesian network of TCM syndrome differentiation were made through the network learning. Then, the constructed system was applied to explore the relationship among the syndrome, the key pattern elements and the syndrome names. The computing results were identical to the diagnostic experience of TCM experts, although it still cannot reflect the comprehensiveness of the thinking ability＂ of doctor＇s syndrome differentiation in TCM. So, the Bayesian network is a good method to deal with the information from the differentiation of symptoms, and can be used to develop the artificial intelligence system for TCM syndrome differentiation.