• DocumentCode
    2379896
  • Title

    Application of Bayesian network in information fusion analysis of four diagnostic methods of traditional Chinese medicine

  • Author

    Xu, Wenjie ; Wang, Yiqin ; Xu, Zhaoxia ; Chen, Chunfeng ; Zou, Xiaojuan

  • Author_Institution
    Lab. of Four Diagnostic Inf. of TCM, Shanghai Univ. of TCM, Shanghai, China
  • fYear
    2010
  • fDate
    18-18 Dec. 2010
  • Firstpage
    694
  • Lastpage
    697
  • Abstract
    Bayesian network is the effective tool for reasoning and modeling of complex and uncertain system based on traditional probability theory, which is widely used in uncertain decision-making, data analysis, intelligence reasoning and other fields. Syndrome differentiation and treatment, one of the basic characteristics of traditional Chinese medicine (TCM), is the essence of TCM. Fusion analysis on standardization and objectification of four diagnostic methods of TCM is the basic of syndrome differentiation analysis of TCM. The traditional methods are often with subjective differentiation and ambiguity, and the essence of syndrome differentiation of TCM can be seen as a classification problem. Bayesian network, as a better algorithm of data mining, is being increasingly applied to the study of syndrome differentiation of TCM. This article outlines the application of Bayesian network in information fusion analysis of four diagnostic methods of TCM and prospects for future research.
  • Keywords
    belief networks; data mining; decision making; medical diagnostic computing; patient treatment; Bayesian network; TCM; data mining; decision making; information fusion analysis; intelligence reasoning; objectification; standardization; syndrome differentiation analysis; traditional Chinese medicine; Bayesian network; information fusion; traditional Chinese medical diagnosis;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Bioinformatics and Biomedicine Workshops (BIBMW), 2010 IEEE International Conference on
  • Conference_Location
    Hong, Kong
  • Print_ISBN
    978-1-4244-8303-7
  • Electronic_ISBN
    978-1-4244-8304-4
  • Type

    conf

  • DOI
    10.1109/BIBMW.2010.5703891
  • Filename
    5703891