Heart rhythm characterization through induced physiological variables

Abstract Atrial fibrillation remains a major cause of morbi-mortality, making mass screening desirable and leading industry to actively develop devices devoted to automatic AF detection. Because there is a tendency toward mobile devices, there is a need for an accurate, rapid method for studying sho...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Jean-François Pons, Zouhair Haddi, Jean-Claude Deharo, Ahmed Charaï, Rachid Bouchakour, Mustapha Ouladsine, Stéphane Delliaux
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2017
Materias:
R
Q
Acceso en línea:https://doaj.org/article/5936510a7b034d3a8145ff7d0f4df1f8
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:5936510a7b034d3a8145ff7d0f4df1f8
record_format dspace
spelling oai:doaj.org-article:5936510a7b034d3a8145ff7d0f4df1f82021-12-02T16:06:19ZHeart rhythm characterization through induced physiological variables10.1038/s41598-017-04998-72045-2322https://doaj.org/article/5936510a7b034d3a8145ff7d0f4df1f82017-07-01T00:00:00Zhttps://doi.org/10.1038/s41598-017-04998-7https://doaj.org/toc/2045-2322Abstract Atrial fibrillation remains a major cause of morbi-mortality, making mass screening desirable and leading industry to actively develop devices devoted to automatic AF detection. Because there is a tendency toward mobile devices, there is a need for an accurate, rapid method for studying short inter-beat interval time series for real-time automatic medical monitoring. We report a new methodology to efficiently select highly discriminative variables between physiological states, here a normal sinus rhythm or atrial fibrillation. We generate induced variables using the first ten time derivatives of an RR interval time series and formally express a new multivariate metric quantifying their discriminative power to drive state variable selection. When combined with a simple classifier, this new methodology results in 99.9% classification accuracy for 1-min RR interval time series (n = 7,400), with heart rate accelerations and jerks being the most discriminant variables. We show that the RR interval time series can be drastically reduced from 60 s to 3 s, with a classification accuracy of 95.0%. We show that heart rhythm characterization is facilitated by induced variables using time derivatives, which is a generic methodology that is particularly suitable to real-time medical monitoring.Jean-François PonsZouhair HaddiJean-Claude DeharoAhmed CharaïRachid BouchakourMustapha OuladsineStéphane DelliauxNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 7, Iss 1, Pp 1-13 (2017)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Jean-François Pons
Zouhair Haddi
Jean-Claude Deharo
Ahmed Charaï
Rachid Bouchakour
Mustapha Ouladsine
Stéphane Delliaux
Heart rhythm characterization through induced physiological variables
description Abstract Atrial fibrillation remains a major cause of morbi-mortality, making mass screening desirable and leading industry to actively develop devices devoted to automatic AF detection. Because there is a tendency toward mobile devices, there is a need for an accurate, rapid method for studying short inter-beat interval time series for real-time automatic medical monitoring. We report a new methodology to efficiently select highly discriminative variables between physiological states, here a normal sinus rhythm or atrial fibrillation. We generate induced variables using the first ten time derivatives of an RR interval time series and formally express a new multivariate metric quantifying their discriminative power to drive state variable selection. When combined with a simple classifier, this new methodology results in 99.9% classification accuracy for 1-min RR interval time series (n = 7,400), with heart rate accelerations and jerks being the most discriminant variables. We show that the RR interval time series can be drastically reduced from 60 s to 3 s, with a classification accuracy of 95.0%. We show that heart rhythm characterization is facilitated by induced variables using time derivatives, which is a generic methodology that is particularly suitable to real-time medical monitoring.
format article
author Jean-François Pons
Zouhair Haddi
Jean-Claude Deharo
Ahmed Charaï
Rachid Bouchakour
Mustapha Ouladsine
Stéphane Delliaux
author_facet Jean-François Pons
Zouhair Haddi
Jean-Claude Deharo
Ahmed Charaï
Rachid Bouchakour
Mustapha Ouladsine
Stéphane Delliaux
author_sort Jean-François Pons
title Heart rhythm characterization through induced physiological variables
title_short Heart rhythm characterization through induced physiological variables
title_full Heart rhythm characterization through induced physiological variables
title_fullStr Heart rhythm characterization through induced physiological variables
title_full_unstemmed Heart rhythm characterization through induced physiological variables
title_sort heart rhythm characterization through induced physiological variables
publisher Nature Portfolio
publishDate 2017
url https://doaj.org/article/5936510a7b034d3a8145ff7d0f4df1f8
work_keys_str_mv AT jeanfrancoispons heartrhythmcharacterizationthroughinducedphysiologicalvariables
AT zouhairhaddi heartrhythmcharacterizationthroughinducedphysiologicalvariables
AT jeanclaudedeharo heartrhythmcharacterizationthroughinducedphysiologicalvariables
AT ahmedcharai heartrhythmcharacterizationthroughinducedphysiologicalvariables
AT rachidbouchakour heartrhythmcharacterizationthroughinducedphysiologicalvariables
AT mustaphaouladsine heartrhythmcharacterizationthroughinducedphysiologicalvariables
AT stephanedelliaux heartrhythmcharacterizationthroughinducedphysiologicalvariables
_version_ 1718385023095144448