The electrocardiogram endeavour: from the Holter single-lead recordings to multilead wearable devices supported by computational machine learning algorithms

Panos Vardas; Martin Cowie; Nikolaos Dagres; Dimitrios Asvestas; Stylianos Tzeis; Emmanuel P Vardas; Gerhard Hindricks; John Camm

doi:10.1093/europace/euz249

The electrocardiogram endeavour: from the Holter single-lead recordings to multilead wearable devices supported by computational machine learning algorithms

Europace. 2020 Jan 1;22(1):19-23. doi: 10.1093/europace/euz249.

Authors

Panos Vardas¹, Martin Cowie², Nikolaos Dagres³, Dimitrios Asvestas⁴, Stylianos Tzeis⁴, Emmanuel P Vardas⁵, Gerhard Hindricks³, John Camm⁶

Affiliations

¹ Heart Sector, Hygeia Hospitals Group, Athens, Greece.
² Imperial College London, London, UK.
³ Department of Electrophysiology, Heart Center Leipzig at the University of Leipzig, Leipzig, Germany.
⁴ Cardiology Department, Mitera General Hospital, Hygeia Group, Athens, Greece.
⁵ 251 Airforce General Hospital, Athens, Greece.
⁶ St. George's University of London, London, UK.

PMID: 31535151
DOI: 10.1093/europace/euz249

Abstract

This review aims to provide a comprehensive recapitulation of the evolution in the field of cardiac rhythm monitoring, shedding light in recent progress made in multilead ECG systems and wearable devices, with emphasis on the promising role of the artificial intelligence and computational techniques in the detection of cardiac abnormalities.

Keywords: Electrocardiogram; Electrocardiography; Machine learning algorithms; Multilead wearable devices.

Publication types

Review

MeSH terms

Algorithms
Artificial Intelligence*
Electrocardiography
Humans
Machine Learning
Signal Processing, Computer-Assisted
Wearable Electronic Devices*