Atrial fibrillation detection using photo-plethysmography and acceleration data at the wrist

A.G. Bonomi, F. Schipper, L.M. Eerikäinen, J. Margarito, R.M. Aarts, S. Babaeizadeh, H.M. de Morree, L.R.C. Dekker

Research output: Contribution to journalArticleAcademic

19 Citations (Scopus)
59 Downloads (Pure)

Abstract

Atrial fibrillation (AF) is a pathological cardiac
condition leading to increased risk for embolic stroke.
Screening for AF is challenging due to the paroxysmal and
asymptomatic nature of the condition. We aimed to
investigate whether an unobtrusive wrist-wearable device
equipped with a photo-plethysmographic (PPG) and
acceleration sensor could detect AF. Sixteen patients with
suspected AF were monitored for 24 hours in an outpatient
setting using a Holter ECG. Simultaneously, PPG and
acceleration data were collected at the wrist. PPG data
was processed to determine the timing of heartbeats and
inter-beat-interval (IBI). Wrist acceleration and PPG
morphology were used to discard IBIs in presence of
motion artefacts. An ECG validated first-order Markov
model was used to assess the probability of irregular
rhythm due to AF using PPG-derived IBIs. The AF
detection algorithm was compared with clinical
adjudications of AF episodes after review of the ECG
records. AF detection was achieved with 97 ± 2%
sensitivity and 99 ± 3% specificity. Due to motion
artefacts, the algorithm did not provide AF classification
for an average of 36 ± 9% of the 24 hours monitoring. We
concluded that a wrist-wearable device equipped with a
PPG and acceleration sensor can accurately detect rhythm
irregularities caused by AF in daily life.
Original languageEnglish
Pages (from-to)277-280
JournalComputing in Cardiology
Volume43
DOIs
Publication statusPublished - 2016
Event43rd Computing in Cardiology Conference (CinC 2016) - Vancouver, Canada
Duration: 11 Sep 201614 Sep 2016
Conference number: 43

Fingerprint

Photoplethysmography
Plethysmography
Wrist
Electrocardiography
Atrial Fibrillation
Sensors
Screening
Monitoring
Artifacts
Stroke

Cite this

Bonomi, A.G. ; Schipper, F. ; Eerikäinen, L.M. ; Margarito, J. ; Aarts, R.M. ; Babaeizadeh, S. ; de Morree, H.M. ; Dekker, L.R.C. / Atrial fibrillation detection using photo-plethysmography and acceleration data at the wrist. In: Computing in Cardiology. 2016 ; Vol. 43. pp. 277-280.
@article{1c87fa1a32a5464e9775afb98f0a1139,
title = "Atrial fibrillation detection using photo-plethysmography and acceleration data at the wrist",
abstract = "Atrial fibrillation (AF) is a pathological cardiaccondition leading to increased risk for embolic stroke.Screening for AF is challenging due to the paroxysmal andasymptomatic nature of the condition. We aimed toinvestigate whether an unobtrusive wrist-wearable deviceequipped with a photo-plethysmographic (PPG) andacceleration sensor could detect AF. Sixteen patients withsuspected AF were monitored for 24 hours in an outpatientsetting using a Holter ECG. Simultaneously, PPG andacceleration data were collected at the wrist. PPG datawas processed to determine the timing of heartbeats andinter-beat-interval (IBI). Wrist acceleration and PPGmorphology were used to discard IBIs in presence ofmotion artefacts. An ECG validated first-order Markovmodel was used to assess the probability of irregularrhythm due to AF using PPG-derived IBIs. The AFdetection algorithm was compared with clinicaladjudications of AF episodes after review of the ECGrecords. AF detection was achieved with 97 ± 2{\%}sensitivity and 99 ± 3{\%} specificity. Due to motionartefacts, the algorithm did not provide AF classificationfor an average of 36 ± 9{\%} of the 24 hours monitoring. Weconcluded that a wrist-wearable device equipped with aPPG and acceleration sensor can accurately detect rhythmirregularities caused by AF in daily life.",
author = "A.G. Bonomi and F. Schipper and L.M. Eerik{\"a}inen and J. Margarito and R.M. Aarts and S. Babaeizadeh and {de Morree}, H.M. and L.R.C. Dekker",
year = "2016",
doi = "10.22489/CinC.2016.081-339",
language = "English",
volume = "43",
pages = "277--280",
journal = "Computing in Cardiology",
issn = "2325-8861",
publisher = "Institute of Electrical and Electronics Engineers",

}

Atrial fibrillation detection using photo-plethysmography and acceleration data at the wrist. / Bonomi, A.G.; Schipper, F.; Eerikäinen, L.M.; Margarito, J.; Aarts, R.M.; Babaeizadeh, S.; de Morree, H.M.; Dekker, L.R.C.

In: Computing in Cardiology, Vol. 43, 2016, p. 277-280.

Research output: Contribution to journalArticleAcademic

TY - JOUR

T1 - Atrial fibrillation detection using photo-plethysmography and acceleration data at the wrist

AU - Bonomi, A.G.

AU - Schipper, F.

AU - Eerikäinen, L.M.

AU - Margarito, J.

AU - Aarts, R.M.

AU - Babaeizadeh, S.

AU - de Morree, H.M.

AU - Dekker, L.R.C.

PY - 2016

Y1 - 2016

N2 - Atrial fibrillation (AF) is a pathological cardiaccondition leading to increased risk for embolic stroke.Screening for AF is challenging due to the paroxysmal andasymptomatic nature of the condition. We aimed toinvestigate whether an unobtrusive wrist-wearable deviceequipped with a photo-plethysmographic (PPG) andacceleration sensor could detect AF. Sixteen patients withsuspected AF were monitored for 24 hours in an outpatientsetting using a Holter ECG. Simultaneously, PPG andacceleration data were collected at the wrist. PPG datawas processed to determine the timing of heartbeats andinter-beat-interval (IBI). Wrist acceleration and PPGmorphology were used to discard IBIs in presence ofmotion artefacts. An ECG validated first-order Markovmodel was used to assess the probability of irregularrhythm due to AF using PPG-derived IBIs. The AFdetection algorithm was compared with clinicaladjudications of AF episodes after review of the ECGrecords. AF detection was achieved with 97 ± 2%sensitivity and 99 ± 3% specificity. Due to motionartefacts, the algorithm did not provide AF classificationfor an average of 36 ± 9% of the 24 hours monitoring. Weconcluded that a wrist-wearable device equipped with aPPG and acceleration sensor can accurately detect rhythmirregularities caused by AF in daily life.

AB - Atrial fibrillation (AF) is a pathological cardiaccondition leading to increased risk for embolic stroke.Screening for AF is challenging due to the paroxysmal andasymptomatic nature of the condition. We aimed toinvestigate whether an unobtrusive wrist-wearable deviceequipped with a photo-plethysmographic (PPG) andacceleration sensor could detect AF. Sixteen patients withsuspected AF were monitored for 24 hours in an outpatientsetting using a Holter ECG. Simultaneously, PPG andacceleration data were collected at the wrist. PPG datawas processed to determine the timing of heartbeats andinter-beat-interval (IBI). Wrist acceleration and PPGmorphology were used to discard IBIs in presence ofmotion artefacts. An ECG validated first-order Markovmodel was used to assess the probability of irregularrhythm due to AF using PPG-derived IBIs. The AFdetection algorithm was compared with clinicaladjudications of AF episodes after review of the ECGrecords. AF detection was achieved with 97 ± 2%sensitivity and 99 ± 3% specificity. Due to motionartefacts, the algorithm did not provide AF classificationfor an average of 36 ± 9% of the 24 hours monitoring. Weconcluded that a wrist-wearable device equipped with aPPG and acceleration sensor can accurately detect rhythmirregularities caused by AF in daily life.

U2 - 10.22489/CinC.2016.081-339

DO - 10.22489/CinC.2016.081-339

M3 - Article

VL - 43

SP - 277

EP - 280

JO - Computing in Cardiology

JF - Computing in Cardiology

SN - 2325-8861

ER -