中医治疗失眠处方数据挖掘研究-中国中医药图书情报杂志.PDFVIP

• 16 • Chinese Journal of Library and Information Science for Traditional Chinese Medicine Feb. 2015 Vol. 39 No. 1 中医治疗失眠处方数据挖掘研究 雷蕾，温先荣，杨硕，李园白，邢雁辉，储戟农，崔蒙* 中国中医科学院中医药信息研究所，北京 100700 摘要：目的 使用关联规则挖掘治疗失眠中药的高频组合以及强关联关系，探讨中药的用药规律。 方法 本文基于 1685 篇中医药临床文献，从临床治疗失眠的方剂出发，将 Rapidminer 5.2 作为数据挖 掘软件，使用关联规则挖掘算法 FP-growth，找到中药之间的高频组合以及强关联关系，并从中医机理 的角度对数据挖掘结果进行解释。结果 在1685 篇临床文献中，治疗失眠的方剂共有768 首，中药407 味。使用频次最高的中药为酸枣仁。通过关联规则挖掘得到1234 个中药组合，其中甘草和酸枣仁是支持 度最高的中药组合，“地黄，桃仁→当归”是置信度最高的中药组合。结论 临床上多采用滋阴降火、补 脾益气、补脾益心等方法治疗失眠。 关键词：失眠；关联规则；中药处方；药食同源中药；Rapidminer 5.2 doi: 10.3969/j.issn.2095-5707.2015.01.004 Study on Traditional Chinese Medicine Prescriptions for Curing Insomnia Based on Association Rules Mining * LEI Lei, WEN Xian-rong, YANG Shuo, LI Yuan-bai, XING Yan-hui, CHU Ji-nong, CUI Meng (Institute of Information on Traditional Chinese Medicine, China Academy of Chinese Medical Sciences, Beijing 100700, China) Abstract: Objective To analyze medicine using regularity of traditional Chinese medicine (TCM) by using association rules mining to find out high-frequency combinations and strong incidence relation of TCM to cure insomnia. Methods Based on 1685 TCM clinical articles, this article started from TCM prescriptions for curing insomnia, set Rapidminer 5.2 as data mining software, used association rules to mine FP-growth, with purposes to find out high-frequency combinations and strong incidence relation, and to elaborate the results of data mining from the aspect of TCM mechanism. Results In the 1685 clinical articles, there were 407 Chinese medicinal herbs in 768 prescriptions for curing insomnia. Ziziphi Spinosae Semen was used with the highest