Automated Musical Rhythm Transcription of ECG RR Interval Time Series as a Tool for Representing Rhythm Variations and Annotation Anomalies in Arrhythmia Heartbeat Classifications

Gonzalo Romero-Garcia*, Paul Lascabettes, Elaine Chew

*Corresponding author for this work

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

10 Downloads (Pure)

Abstract

We introduce a linear time algorithm for transcribing RR intervals into musical rhythms using approximate common divisors (ACDs). The technique maps ACDs to nodes on a graph, node transitions represent heart rate variations; a balance must be struck between rhythmic changes and heart rate variation. Possible transcriptions correspond to paths in the ACD graph. Given a set of weights, a shortest path algorithm finds the optimal transcription. The representation facilitates efficient pattern recognition and extraction. The transcription technique is applied to the Physionet Long Term Atrial Fibrillation Database to demonstrate how it shows the rhythmic variation within heartbeat subsequences having the same labels, and its utility in detecting potential labelling errors on its own and via a rhythm simplex. Further work may explore prospective applications to arrhythmia stratification.
Original languageEnglish
Title of host publicationComputing in Cardiology 2022
PublisherIEEE Xplore
Volume498
DOIs
Publication statusPublished - 7 Sept 2022
EventComputing in Cardiology 2022 - Tampere, Finland
Duration: 4 Sept 20227 Sept 2022
https://events.tuni.fi/cinc2022/

Conference

ConferenceComputing in Cardiology 2022
Abbreviated titleCinC2022
Country/TerritoryFinland
CityTampere
Period4/09/20227/09/2022
Internet address

Keywords

  • ECG intervals
  • ECG algorithm
  • rhythm transcription

Fingerprint

Dive into the research topics of 'Automated Musical Rhythm Transcription of ECG RR Interval Time Series as a Tool for Representing Rhythm Variations and Annotation Anomalies in Arrhythmia Heartbeat Classifications'. Together they form a unique fingerprint.

Cite this