AF Detection by Exploiting the Spectral and Temporal Characteristics of ECG Signals with the LSTM Model

Yen Chun Chang, Sau-Hsuan Wu*, Li Ming Tseng, Hsi-Lu Chao, Chun Hsien Ko

*Corresponding author for this work

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

8 Scopus citations

Abstract

This research reinvestigates the detection of atrial fibrillation (AF) from a recurrent neural network (RNN) viewpoint. In particular, a long short-term memory (LSTM) model of RNN is designed to exploit the high-order spectral and temporal features of the multi-lead electrocardiogram (ECG) signals of patients with AF. To verify the proposed method, the LSTM model is tested with ECG data available from the PhysioNet and some normal ECG data collected in our labs. The results show that not only the deviation of the so-called RR intervals of ECG signals but also its temporal variations are critical to AF detection. The accuracy of AF detection can reach up to 98.3 %, with an LSTM model of using 30 hidden units. Considering more realistic applications, we further tested the model with subjects different from that of the training data. The accuracy is about 87% with high sensitivity. The experimental results show that the proposed model is able to effectively extract both the long-term and short-term characteristics of the spectral content of the AF ECG signals, making it a good candidate model for AF detection.

Original languageEnglish
Title of host publicationComputing in Cardiology Conference, CinC 2018
PublisherIEEE Computer Society
ISBN (Electronic)9781728109589
DOIs
StatePublished - 1 Sep 2018
Event45th Computing in Cardiology Conference, CinC 2018 - Maastricht, Netherlands
Duration: 23 Sep 201826 Sep 2018

Publication series

NameComputing in Cardiology
Volume2018-September
ISSN (Print)2325-8861
ISSN (Electronic)2325-887X

Conference

Conference45th Computing in Cardiology Conference, CinC 2018
CountryNetherlands
CityMaastricht
Period23/09/1826/09/18

Fingerprint Dive into the research topics of 'AF Detection by Exploiting the Spectral and Temporal Characteristics of ECG Signals with the LSTM Model'. Together they form a unique fingerprint.

Cite this