自己組織化マップを用いた透析シャント音による狭窄診断支援装置  [in Japanese] An Auscultaiting Diagnosis Support System for Assessing Hemodialysis Shunt Stenosis by Using Self-organizing Map  [in Japanese]

Access this Article

Search this Article

Author(s)

Abstract

Vascular access for hemodialysis is a lifeline for over 280,000 chronic renal failure patients in Japan. Early detection of stenosis may facilitate long-term use of hemodialysis shunts. Stethoscope auscultation of vascular murmurs has some utility in the assessment of access patency; however, the sensitivity of this diagnostic approach is skill dependent. This study proposes a novel diagnosis support system to detect stenosis by using vascular murmurs. The system is based on a self-organizing map (SOM) and short-time maximum entropy method (STMEM) for data analysis. SOM is an artificial neural network, which is trained using unsupervised learning to produce a feature map that is useful for visualizing the analogous relationship between input data. The author recorded vascular murmurs before and after percutaneous transluminal angioplasty (PTA). The SOM-based classification was consistent with to the classification based on MEM spectral and spectrogram characteristics. The ratio of pre-PTA murmurs in the stenosis category was much higher than the post-PTA murmurs. The results suggest that the proposed method may be an effective tool in the determination of shunt stenosis.

Journal

  • IEEJ Transactions on Electronics, Information and Systems

    IEEJ Transactions on Electronics, Information and Systems 131(1), 160-166, 2011-01-01

    The Institute of Electrical Engineers of Japan

References:  18

Cited by:  2

Codes

  • NII Article ID (NAID)
    10027636900
  • NII NACSIS-CAT ID (NCID)
    AN10065950
  • Text Lang
    JPN
  • Article Type
    Journal Article
  • ISSN
    03854221
  • NDL Article ID
    10933714
  • NDL Source Classification
    ZN31(科学技術--電気工学・電気機械工業)
  • NDL Call No.
    Z16-795
  • Data Source
    CJP  CJPref  NDL  J-STAGE 
Page Top