Atrial electrical activity detection in the 12-lead ECG using synthetic atrial activity signals

Or Perlman, Amos Katz, Noam Weissman, Yaniv Zigel

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

A significant key for the success of arrhythmia diagnosis using ECG is detecting the atrial electrical activity (AEA). Despite extensive research, there is a diagnostic problem in detecting AEA in some arrhythmias, especially when the AEA-wave is hidden in other waves. Our proposed method utilizes the well-known linear combiner usually used for noise reduction, and adapted it for AEA detection. The physician/user marks one prominent AEA segment. Then, a synthetic signal is created that contains an isoelectric line in addition to a Gaussian in the delineated segment. The 6 precordial leads, lead I, and lead II, serve as reference signals, so by finding the appropriate weight coefficients, their linear combination is forced to converge to a signal that is similar to the AEA signal. At the final stage, the resulting signal is band-pass filtered and the peaks higher than a certain threshold are determined to be AEA-waves. Sensitivity of 94.0% and precision of 90.2% were achieved in detecting AEA from the standard 12-lead ECG for various arrhythmia types.

Original languageEnglish
Title of host publicationComputing in Cardiology 2012, CinC 2012
Pages665-668
Number of pages4
StatePublished - 1 Dec 2012
Event39th Computing in Cardiology Conference, CinC 2012 - Krakow, Poland
Duration: 9 Sep 201212 Sep 2012

Publication series

NameComputing in Cardiology
Volume39

Conference

Conference39th Computing in Cardiology Conference, CinC 2012
Country/TerritoryPoland
CityKrakow
Period9/09/1212/09/12

All Science Journal Classification (ASJC) codes

  • Cardiology and Cardiovascular Medicine
  • General Computer Science

Fingerprint

Dive into the research topics of 'Atrial electrical activity detection in the 12-lead ECG using synthetic atrial activity signals'. Together they form a unique fingerprint.

Cite this