Artificial intelligence for the detection, prediction, and management of atrial fibrillation

Jonas L Isaksen; Mathias Baumert; Astrid N L Hermans; Molly Maleckar; Dominik Linz

doi:10.1007/s00399-022-00839-x

Artificial intelligence for the detection, prediction, and management of atrial fibrillation

Jonas L Isaksen, Mathias Baumert, Astrid N L Hermans, Molly Maleckar, Dominik Linz^*

^*Corresponding author for this work

Research output: Contribution to journal › (Systematic) Review article › peer-review

Abstract

The present article reviews the state of the art of machine learning algorithms for the detection, prediction, and management of atrial fibrillation (AF), as well as of the development and evaluation of artificial intelligence (AI) in cardiology and beyond. Today, AI detects AF with a high accuracy using 12-lead or single-lead electrocardiograms or photoplethysmography. The prediction of paroxysmal or future AF currently operates at a level of precision that is too low for clinical use. Further studies are needed to determine whether patient selection for interventions may be possible with machine learning.

Original language	English
Pages (from-to)	34-41
Number of pages	8
Journal	Herzschrittmachertherapie und Elektrophysiologie
Volume	33
Issue number	1
DOIs	https://doi.org/10.1007/s00399-022-00839-x
Publication status	Published - Mar 2022

Keywords

Algorithms
Artificial Intelligence
Atrial Fibrillation/diagnosis
Electrocardiography
Humans
Machine Learning

Access to Document

10.1007/s00399-022-00839-xLicence: CC BY

Cite this

@article{fa72eb94608b44ad8905b7f5bc18ff85,

title = "Artificial intelligence for the detection, prediction, and management of atrial fibrillation",

abstract = "The present article reviews the state of the art of machine learning algorithms for the detection, prediction, and management of atrial fibrillation (AF), as well as of the development and evaluation of artificial intelligence (AI) in cardiology and beyond. Today, AI detects AF with a high accuracy using 12-lead or single-lead electrocardiograms or photoplethysmography. The prediction of paroxysmal or future AF currently operates at a level of precision that is too low for clinical use. Further studies are needed to determine whether patient selection for interventions may be possible with machine learning.",

keywords = "Algorithms, Artificial Intelligence, Atrial Fibrillation/diagnosis, Electrocardiography, Humans, Machine Learning",

author = "Isaksen, {Jonas L} and Mathias Baumert and Hermans, {Astrid N L} and Molly Maleckar and Dominik Linz",

note = "{\textcopyright} 2022. The Author(s).",

year = "2022",

month = mar,

doi = "10.1007/s00399-022-00839-x",

language = "English",

volume = "33",

pages = "34--41",

journal = "Herzschrittmachertherapie und Elektrophysiologie",

issn = "0938-7412",

publisher = "D. Steinkopff-Verlag",

number = "1",

}

TY - JOUR

T1 - Artificial intelligence for the detection, prediction, and management of atrial fibrillation

AU - Isaksen, Jonas L

AU - Baumert, Mathias

AU - Hermans, Astrid N L

AU - Maleckar, Molly

AU - Linz, Dominik

PY - 2022/3

Y1 - 2022/3

N2 - The present article reviews the state of the art of machine learning algorithms for the detection, prediction, and management of atrial fibrillation (AF), as well as of the development and evaluation of artificial intelligence (AI) in cardiology and beyond. Today, AI detects AF with a high accuracy using 12-lead or single-lead electrocardiograms or photoplethysmography. The prediction of paroxysmal or future AF currently operates at a level of precision that is too low for clinical use. Further studies are needed to determine whether patient selection for interventions may be possible with machine learning.

AB - The present article reviews the state of the art of machine learning algorithms for the detection, prediction, and management of atrial fibrillation (AF), as well as of the development and evaluation of artificial intelligence (AI) in cardiology and beyond. Today, AI detects AF with a high accuracy using 12-lead or single-lead electrocardiograms or photoplethysmography. The prediction of paroxysmal or future AF currently operates at a level of precision that is too low for clinical use. Further studies are needed to determine whether patient selection for interventions may be possible with machine learning.

KW - Algorithms

KW - Artificial Intelligence

KW - Atrial Fibrillation/diagnosis

KW - Electrocardiography

KW - Humans

KW - Machine Learning

U2 - 10.1007/s00399-022-00839-x

DO - 10.1007/s00399-022-00839-x

M3 - (Systematic) Review article

C2 - 35147766

SN - 0938-7412

VL - 33

SP - 34

EP - 41

JO - Herzschrittmachertherapie und Elektrophysiologie

JF - Herzschrittmachertherapie und Elektrophysiologie

IS - 1

ER -

Artificial intelligence for the detection, prediction, and management of atrial fibrillation

Abstract

Keywords

Access to Document

Fingerprint

Cite this