Detail
Article
Online article
FT
Medvik - BMC
  • Something wrong with this record ?

A machine learning algorithm for electrocardiographic fQRS quantification validated on multi-center data

A. Villa, B. Vandenberk, T. Kenttä, S. Ingelaere, HV. Huikuri, M. Zabel, T. Friede, C. Sticherling, A. Tuinenburg, M. Malik, S. Van Huffel, R. Willems, C. Varon

. 2022 ; 12 (1) : 6783. [pub] 20220426

Language English Country Great Britain

Document type Journal Article, Research Support, Non-U.S. Gov't

Persistent link   https://www.medvik.cz/link/bmc22018719

Fragmented QRS (fQRS) is an electrocardiographic (ECG) marker of myocardial conduction abnormality, characterized by additional notches in the QRS complex. The presence of fQRS has been associated with an increased risk of all-cause mortality and arrhythmia in patients with cardiovascular disease. However, current binary visual analysis is prone to intra- and inter-observer variability and different definitions are problematic in clinical practice. Therefore, objective quantification of fQRS is needed and could further improve risk stratification of these patients. We present an automated method for fQRS detection and quantification. First, a novel robust QRS complex segmentation strategy is proposed, which combines multi-lead information and excludes abnormal heartbeats automatically. Afterwards extracted features, based on variational mode decomposition (VMD), phase-rectified signal averaging (PRSA) and the number of baseline-crossings of the ECG, were used to train a machine learning classifier (Support Vector Machine) to discriminate fragmented from non-fragmented ECG-traces using multi-center data and combining different fQRS criteria used in clinical settings. The best model was trained on the combination of two independent previously annotated datasets and, compared to these visual fQRS annotations, achieved Kappa scores of 0.68 and 0.44, respectively. We also show that the algorithm might be used in both regular sinus rhythm and irregular beats during atrial fibrillation. These results demonstrate that the proposed approach could be relevant for clinical practice by objectively assessing and quantifying fQRS. The study sets the path for further clinical application of the developed automated fQRS algorithm.

References provided by Crossref.org

000      
00000naa a2200000 a 4500
001      
bmc22018719
003      
CZ-PrNML
005      
20220804135039.0
007      
ta
008      
220720s2022 xxk f 000 0|eng||
009      
AR
024    7_
$a 10.1038/s41598-022-10452-0 $2 doi
035    __
$a (PubMed)35474073
040    __
$a ABA008 $b cze $d ABA008 $e AACR2
041    0_
$a eng
044    __
$a xxk
100    1_
$a Villa, Amalia $u Department of Electrical Engineering (ESAT), STADIUS Center for Dynamical Systems, Signal Processing and Data Analytics, KU Leuven, Leuven, Belgium. amalia.villagomez@kuleuven.be
245    12
$a A machine learning algorithm for electrocardiographic fQRS quantification validated on multi-center data / $c A. Villa, B. Vandenberk, T. Kenttä, S. Ingelaere, HV. Huikuri, M. Zabel, T. Friede, C. Sticherling, A. Tuinenburg, M. Malik, S. Van Huffel, R. Willems, C. Varon
520    9_
$a Fragmented QRS (fQRS) is an electrocardiographic (ECG) marker of myocardial conduction abnormality, characterized by additional notches in the QRS complex. The presence of fQRS has been associated with an increased risk of all-cause mortality and arrhythmia in patients with cardiovascular disease. However, current binary visual analysis is prone to intra- and inter-observer variability and different definitions are problematic in clinical practice. Therefore, objective quantification of fQRS is needed and could further improve risk stratification of these patients. We present an automated method for fQRS detection and quantification. First, a novel robust QRS complex segmentation strategy is proposed, which combines multi-lead information and excludes abnormal heartbeats automatically. Afterwards extracted features, based on variational mode decomposition (VMD), phase-rectified signal averaging (PRSA) and the number of baseline-crossings of the ECG, were used to train a machine learning classifier (Support Vector Machine) to discriminate fragmented from non-fragmented ECG-traces using multi-center data and combining different fQRS criteria used in clinical settings. The best model was trained on the combination of two independent previously annotated datasets and, compared to these visual fQRS annotations, achieved Kappa scores of 0.68 and 0.44, respectively. We also show that the algorithm might be used in both regular sinus rhythm and irregular beats during atrial fibrillation. These results demonstrate that the proposed approach could be relevant for clinical practice by objectively assessing and quantifying fQRS. The study sets the path for further clinical application of the developed automated fQRS algorithm.
650    _2
$a algoritmy $7 D000465
650    12
$a fibrilace síní $x diagnóza $7 D001281
650    12
$a elektrokardiografie $x metody $7 D004562
650    _2
$a lidé $7 D006801
650    _2
$a strojové učení $7 D000069550
650    _2
$a support vector machine $7 D060388
655    _2
$a časopisecké články $7 D016428
655    _2
$a práce podpořená grantem $7 D013485
700    1_
$a Vandenberk, Bert $u Department of Cardiovascular Diseases, Experimental Cardiology, KU Leuven, Leuven, Belgium $u Department of Cardiac Sciences, Libin Cardiovascular Institute, Cumming School of Medicine, University of Calgary, Calgary, Alberta, Canada
700    1_
$a Kenttä, Tuomas $u Research Unit of Internal Medicine, Medical Research Center Oulu, University of Oulu and Oulu University Hospital, Oulu, Finland
700    1_
$a Ingelaere, Sebastian $u Department of Cardiovascular Diseases, Experimental Cardiology, KU Leuven, Leuven, Belgium
700    1_
$a Huikuri, Heikki V $u Research Unit of Internal Medicine, Medical Research Center Oulu, University of Oulu and Oulu University Hospital, Oulu, Finland
700    1_
$a Zabel, Markus $u Department of Cardiology and Pneumology, Heart Center, University of Göttingen Medical Center, Göttingen, Germany
700    1_
$a Friede, Tim $u Department of Medical Statistics, University Medical Center Göttingen, Göttingen, Germany $u DZHK (German Center of Cardiovascular Research), partner site Göttingen, Göttingen, Germany
700    1_
$a Sticherling, Christian $u Division of Cardiology, University of Basel Hospital, Basel, Switzerland
700    1_
$a Tuinenburg, Anton $u Department of Cardiology, University Medical Center Utrecht, Utrecht, Netherlands
700    1_
$a Malik, Marek $u National Heart and Lung Institute, Imperial College, London, UK $u Department of Internal Medicine and Cardiology, Masaryk University, Brno, Czech Republic
700    1_
$a Van Huffel, Sabine $u Department of Electrical Engineering (ESAT), STADIUS Center for Dynamical Systems, Signal Processing and Data Analytics, KU Leuven, Leuven, Belgium
700    1_
$a Willems, Rik $u Department of Cardiovascular Diseases, Experimental Cardiology, KU Leuven, Leuven, Belgium
700    1_
$a Varon, Carolina $u Department of Electrical Engineering (ESAT), STADIUS Center for Dynamical Systems, Signal Processing and Data Analytics, KU Leuven, Leuven, Belgium $u Microgravity Research Center, Université Libre de Bruxelles, Brussels, Belgium
773    0_
$w MED00182195 $t Scientific reports $x 2045-2322 $g Roč. 12, č. 1 (2022), s. 6783
856    41
$u https://pubmed.ncbi.nlm.nih.gov/35474073 $y Pubmed
910    __
$a ABA008 $b sig $c sign $y p $z 0
990    __
$a 20220720 $b ABA008
991    __
$a 20220804135033 $b ABA008
999    __
$a ok $b bmc $g 1822369 $s 1169962
BAS    __
$a 3
BAS    __
$a PreBMC
BMC    __
$a 2022 $b 12 $c 1 $d 6783 $e 20220426 $i 2045-2322 $m Scientific reports $n Sci Rep $x MED00182195
LZP    __
$a Pubmed-20220720

Find record

Citation metrics

Archiving options