Detecting atrial fibrillation and atrial flutter in daily life using photoplethysmography data

Linda M. Eerikäinen (Corresponding author), Alberto G. Bonomi, Fons Schipper, Lukas R.C. Dekker, Helma M. de Morree, Rik Vullings, Ronald M. Aarts

Research output: Contribution to journalArticleAcademicpeer-review

Abstract

Objective: Photoplethysmography (PPG) enables unobtrusive heart rate monitoring, which can be used in wrist-worn applications. Its potential for detecting atrial fibrillation (AF) has been recently presented. Besides AF, another cardiac arrhythmia increasing stroke risk and requiring treatment is atrial flutter (AFL). Currently, the knowledge about AFL detection with PPG is limited. The objective of our study was to develop a model that classifies AF, AFL, and sinus rhythm with or without premature beats from PPG and acceleration data measured at the wrist in daily life. Methods: A dataset of 40 patients was collected by measuring PPG and accelerometer data, as well as electrocardiogram as a reference, during 24-hour monitoring. The dataset was split into 75%-25% for training and testing a Random Forest (RF) model, which combines features from PPG, inter-pulse intervals (IPI), and accelerometer data, to classify AF, AFL, and other rhythms. The performance was compared to an AF detection algorithm combining traditional IPI features for determining the robustness of the accuracy in presence of AFL. Results: The RF model classified AF/AFL/other with sensitivity and specificity of 97.6/84.5/98.1% and 98.2/99.7/92.8%, respectively. The results with the IPI-based AF classifier showed that the majority of false detections were caused by AFL. Conclusion: The PPG signal contains information to classify AFL in the presence of AF, sinus rhythm, or sinus rhythm with premature contractions. Significance: PPG could indicate presence of AFL, not only AF.
Original languageEnglish
Number of pages9
JournalIEEE Journal of Biomedical and Health Informatics
DOIs
Publication statusE-pub ahead of print - 12 Nov 2019

Fingerprint

Photoplethysmography
Atrial Flutter
Atrial Fibrillation
Accelerometers
Wrist
Monitoring
Premature Cardiac Complexes
Electrocardiography
Classifiers
Cardiac Arrhythmias
Heart Rate
Stroke
Testing

Keywords

  • Atrial fibrillation
  • Photoplethysmography
  • Accelerometer
  • Atrial flutter
  • Random forest

Cite this

@article{15b5bb10e4b54cd8b13ff6bcfedd7c98,
title = "Detecting atrial fibrillation and atrial flutter in daily life using photoplethysmography data",
abstract = "Objective: Photoplethysmography (PPG) enables unobtrusive heart rate monitoring, which can be used in wrist-worn applications. Its potential for detecting atrial fibrillation (AF) has been recently presented. Besides AF, another cardiac arrhythmia increasing stroke risk and requiring treatment is atrial flutter (AFL). Currently, the knowledge about AFL detection with PPG is limited. The objective of our study was to develop a model that classifies AF, AFL, and sinus rhythm with or without premature beats from PPG and acceleration data measured at the wrist in daily life. Methods: A dataset of 40 patients was collected by measuring PPG and accelerometer data, as well as electrocardiogram as a reference, during 24-hour monitoring. The dataset was split into 75{\%}-25{\%} for training and testing a Random Forest (RF) model, which combines features from PPG, inter-pulse intervals (IPI), and accelerometer data, to classify AF, AFL, and other rhythms. The performance was compared to an AF detection algorithm combining traditional IPI features for determining the robustness of the accuracy in presence of AFL. Results: The RF model classified AF/AFL/other with sensitivity and specificity of 97.6/84.5/98.1{\%} and 98.2/99.7/92.8{\%}, respectively. The results with the IPI-based AF classifier showed that the majority of false detections were caused by AFL. Conclusion: The PPG signal contains information to classify AFL in the presence of AF, sinus rhythm, or sinus rhythm with premature contractions. Significance: PPG could indicate presence of AFL, not only AF.",
keywords = "Atrial fibrillation, Photoplethysmography, Accelerometer, Atrial flutter, Random forest",
author = "Eerik{\"a}inen, {Linda M.} and Bonomi, {Alberto G.} and Fons Schipper and Dekker, {Lukas R.C.} and {de Morree}, {Helma M.} and Rik Vullings and Aarts, {Ronald M.}",
year = "2019",
month = "11",
day = "12",
doi = "10.1109/JBHI.2019.2950574",
language = "English",
journal = "IEEE Journal of Biomedical and Health Informatics",
issn = "2168-2194",
publisher = "Institute of Electrical and Electronics Engineers",

}

TY - JOUR

T1 - Detecting atrial fibrillation and atrial flutter in daily life using photoplethysmography data

AU - Eerikäinen, Linda M.

AU - Bonomi, Alberto G.

AU - Schipper, Fons

AU - Dekker, Lukas R.C.

AU - de Morree, Helma M.

AU - Vullings, Rik

AU - Aarts, Ronald M.

PY - 2019/11/12

Y1 - 2019/11/12

N2 - Objective: Photoplethysmography (PPG) enables unobtrusive heart rate monitoring, which can be used in wrist-worn applications. Its potential for detecting atrial fibrillation (AF) has been recently presented. Besides AF, another cardiac arrhythmia increasing stroke risk and requiring treatment is atrial flutter (AFL). Currently, the knowledge about AFL detection with PPG is limited. The objective of our study was to develop a model that classifies AF, AFL, and sinus rhythm with or without premature beats from PPG and acceleration data measured at the wrist in daily life. Methods: A dataset of 40 patients was collected by measuring PPG and accelerometer data, as well as electrocardiogram as a reference, during 24-hour monitoring. The dataset was split into 75%-25% for training and testing a Random Forest (RF) model, which combines features from PPG, inter-pulse intervals (IPI), and accelerometer data, to classify AF, AFL, and other rhythms. The performance was compared to an AF detection algorithm combining traditional IPI features for determining the robustness of the accuracy in presence of AFL. Results: The RF model classified AF/AFL/other with sensitivity and specificity of 97.6/84.5/98.1% and 98.2/99.7/92.8%, respectively. The results with the IPI-based AF classifier showed that the majority of false detections were caused by AFL. Conclusion: The PPG signal contains information to classify AFL in the presence of AF, sinus rhythm, or sinus rhythm with premature contractions. Significance: PPG could indicate presence of AFL, not only AF.

AB - Objective: Photoplethysmography (PPG) enables unobtrusive heart rate monitoring, which can be used in wrist-worn applications. Its potential for detecting atrial fibrillation (AF) has been recently presented. Besides AF, another cardiac arrhythmia increasing stroke risk and requiring treatment is atrial flutter (AFL). Currently, the knowledge about AFL detection with PPG is limited. The objective of our study was to develop a model that classifies AF, AFL, and sinus rhythm with or without premature beats from PPG and acceleration data measured at the wrist in daily life. Methods: A dataset of 40 patients was collected by measuring PPG and accelerometer data, as well as electrocardiogram as a reference, during 24-hour monitoring. The dataset was split into 75%-25% for training and testing a Random Forest (RF) model, which combines features from PPG, inter-pulse intervals (IPI), and accelerometer data, to classify AF, AFL, and other rhythms. The performance was compared to an AF detection algorithm combining traditional IPI features for determining the robustness of the accuracy in presence of AFL. Results: The RF model classified AF/AFL/other with sensitivity and specificity of 97.6/84.5/98.1% and 98.2/99.7/92.8%, respectively. The results with the IPI-based AF classifier showed that the majority of false detections were caused by AFL. Conclusion: The PPG signal contains information to classify AFL in the presence of AF, sinus rhythm, or sinus rhythm with premature contractions. Significance: PPG could indicate presence of AFL, not only AF.

KW - Atrial fibrillation

KW - Photoplethysmography

KW - Accelerometer

KW - Atrial flutter

KW - Random forest

U2 - 10.1109/JBHI.2019.2950574

DO - 10.1109/JBHI.2019.2950574

M3 - Article

C2 - 31689222

JO - IEEE Journal of Biomedical and Health Informatics

JF - IEEE Journal of Biomedical and Health Informatics

SN - 2168-2194

ER -