基于Python的中医药数据挖掘中标准数据集的加工—以高血压治疗数据为例  

Processing of standard data sets in data mining of traditional Chinese medicine based on Python:taking hypertension treatment data as an example

作　　者：田颖[1] 郭栋[2] 彭伟[3] 范晓艳[4] 张晨岳 朱俊潼 Tian Ying;Guo Dong;Peng Wei;Fan Xiaoyan;Zhang Chenyue;Zhu Juntong(Clinical Research Center,Affiliated Hospital of Shandong University of Traditional Chinese Medicine,Jinan 250014,China;不详)

机构地区：[1]山东中医药大学附属医院临床研究中心,济南250014 [2]山东中医药大学基础医学院,济南250300 [3]山东中医药大学附属医院神经内科,济南250014 [4]山东中医药大学附属医院心内科,济南250014 [5]东华大学理学院,上海200042 [6]山东师范大学科学与工程学院,济南250000

出　　处：《中国循证心血管医学杂志》2023年第5期517-522,528,共7页Chinese Journal of Evidence-Based Cardiovascular Medicine

基　　金：国家中医药管理局全国齐鲁伤寒中医学术流派传承工作室建设项目,国中医药人教函【2019】62号;山东省科技创新基地专项(鲁科字[2018]103号);国家中医药管理局国家中医临床基地业务建设科研专项(JDZX2015141);高血压国家中医临床研究基地建设项目(国中医药发[2008]23号)。

摘　　要：中医药独特的理论体系使得其现代化研究面临着巨大的困难。基于日常医疗信息的真实世界证据为解决随机对照试验不能解决的问题提供了重要的证据支持。当前越来越多的慢病中医药数据库被建立,数据量急剧增加。中医药数据自身的特点使得大量的时间和精力耗费在数据的预处理阶段。本文以Python为例展示快速高效的实现中医药数据挖掘中的标准数据集的加工,以进一步降低中医药数据挖掘的门槛。The unique theoretical system of traditional Chinese medicine(TCM)makes its modernization research facing great difficulties.Real world evidence based on daily medical information provides evidence support for solving the problems cannot be solved by randomized controlled trial(RCT).More and more TCM databases of chronic diseases have been established,and the amount of data has increased sharply.Due to the characteristics of TCM data,a lot of time and energy are spent in the data preprocessing stage.Taking Python as an example,this paper shows how to quickly and efficiently process the standard data set in TCM data mining,so as to further reduce the threshold of TCM data mining.

关 键 词：中医药 数据挖掘 预处理 PYTHON 

分 类 号：R24[医药卫生—中医临床基础]