Computer Engineering and Applications ›› 2010, Vol. 46 ›› Issue (18): 215-219.DOI: 10.3778/j.issn.1002-8331.2010.18.067

• 工程与应用 • Previous Articles     Next Articles

Research and design of electronic patient record mining model based on rough concept lattice

DING Wei-ping1,2,DONG Jian-cheng1,WANG Bin3,SHI Quan1,SHI Zhen-guo1   

  1. 1.School of Computer Science and Technology,Nantong University,Nantong,Jiangsu 226019,China
    2.Provincial Key Laboratory for Computer Information Processing Technology,Soochow University,Suzhou,Jiangsu 215006,China
    3.Third People’s Hospital of Nantong,Nantong,Jiangsu 226007,China
  • Received:2008-12-15 Revised:2010-04-29 Online:2010-06-21 Published:2010-06-21
  • Contact: DING Wei-ping

一种粗糙概念格的电子病历挖掘模型研究与设计

丁卫平1,2,董建成1,王 斌3,施 佺1,石振国1

  

  1. 1.南通大学 计算机科学与技术学院,江苏 南通 226019
    2.苏州大学 江苏省计算机信息处理技术重点实验室,江苏 苏州 215006
    3.南通市第三人民医院,江苏 南通 226007
  • 通讯作者: 丁卫平

Abstract: Electronic patient record mining deals with the implicit and useful medical information stored in the electronic patient record database.And by this technology some useful knowledge is extracted and the scientific and auxiliary decision-making is proved for the diagnosis and treatment of disease.After the correlative ideas of rough sets and concept lattice are studied,the rough concept lattice mining model is presented according to features of the medical data in the electronic patient record database.The key EPRM algorithm is nested into the model.The condition entropy method is adopted to reduce the attributions,and rough decision rule lattice is constructed.The results show that model is better on the mining efficiency,running speed and adaptability.

Key words: rough set, concept lattice, electronic patient record mining, condition entropy, decision rule lattice

摘要: 电子病历挖掘(EPRM)指的是在电子病历数据库中提取有用的医疗信息,并挖掘隐含其中医学诊断规则和模式,为疾病诊断和治疗提供科学的、准确的辅助决策等。在研究粗糙集和概念格基本理论的基础上,结合电子病历数据库中医学数据的特征,提出了基于粗糙概念格电子病历挖掘模型设计方法,该模型采用条件熵对病历大量属性进行约简和粗糙决策规则格的构造算法(EPRM),实验表明该模型在决策规则挖掘效率、运行速度和适应性等方面都具有较好的性能。

关键词: 粗糙集, 概念格, 电子病历挖掘, 条件熵, 决策规则格

CLC Number: