• DocumentCode
    307688
  • Title

    Arrhythmia diagnosis system: validation methodology

  • Author

    Giraldo, B.F. ; Binia, M. ; Marrugat, J. ; Caminal, P.

  • Author_Institution
    Inst. de Cibernetica, CSIC, Barcelona, Spain
  • Volume
    1
  • fYear
    1995
  • fDate
    20-25 Sep 1995
  • Firstpage
    737
  • Abstract
    Presents the implementation of the validation stage of an automatic system for the diagnosis of cardiac arrhythmias based on the Minnesota Code. Exact diagnosis of cardiac arrhythmias implies some degree of uncertainty and to establish a gold standard is not feasible. This automatic system has been developed to provide assistance in the diagnosis of 51 pathologies of cardiac arrhythmias. The system analyzes the electrocardiographic (ECG) signal (time intervals, amplitudes, durations and waveshapes) generating the necessary information for the knowledge-base of cardiac arrhythmias. Next, the authors applied the decision rules and obtain the corresponding diagnosis. The first step in the validation is the analysis of capability of the system to classify between pathological and not-pathological systems. After that, the system selects 100 pathological ECG records from the database to be used at the next validation stage. The validation has been done analysing the diagnoses of clinicians with different levels of competence in arrhythmology
  • Keywords
    electrocardiography; medical expert systems; medical signal processing; Minnesota Code; arrhythmia diagnosis system; arrhythmology; cardiac arrhythmias pathologies; database; decision rules; electrodiagnostics; time intervals; validation methodology; waveshapes; Biomedical signal processing; Databases; Diagnostic expert systems; Electrocardiography; Gold; Hospitals; Medical expert systems; Pathology; Subspace constraints; Uncertainty;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Engineering in Medicine and Biology Society, 1995., IEEE 17th Annual Conference
  • Conference_Location
    Montreal, Que.
  • Print_ISBN
    0-7803-2475-7
  • Type

    conf

  • DOI
    10.1109/IEMBS.1995.575338
  • Filename
    575338