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

. 2022 Apr 26 ; 12 (1) : 6783. [epub] 20220426

Jazyk angličtina Země Anglie, Velká Británie Médium electronic

Typ dokumentu časopisecké články, práce podpořená grantem

Perzistentní odkaz   https://www.medvik.cz/link/pmid35474073
Odkazy

PubMed 35474073
PubMed Central PMC9043208
DOI 10.1038/s41598-022-10452-0
PII: 10.1038/s41598-022-10452-0
Knihovny.cz E-zdroje

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.

Zobrazit více v PubMed

Das MK, Khan B, Jacob S, Kumar A, Mahenthiran J. Significance of a fragmented QRS complex versus a Q wave in patients with coronary artery disease. Circulation. 2006;113(21):2495–2501. doi: 10.1161/CIRCULATIONAHA.105.595892. PubMed DOI

Vandenberk B, et al. Inferior and anterior QRS fragmentation have different prognostic value in patients who received an implantable defibrillator in primary prevention of sudden cardiac death. Int. J. Cardiol. 2017;243:223–228. doi: 10.1016/j.ijcard.2017.02.131. PubMed DOI

Das M. K., et al. Fragmented wide QRS on a 12-lead ECG: a sign of myocardial scar and poor prognosis. Circ. Arrhythm. Electrophysiol. 2008;1(4):258–268. doi: 10.1161/CIRCEP.107.763284. PubMed DOI

Vandenberk B, et al. Inter-and intra-observer variability of visual fragmented QRS scoring in ischemic and non-ischemic cardiomyopathy. J. Electrocardiol. 2018;51(3):549–554. doi: 10.1016/j.jelectrocard.2017.12.002. PubMed DOI

Torigoe K, et al. The number of leads with fragmented QRS is independently associated with cardiac death or hospitalization for heart failure in patients with prior myocardial infarction. J. Cardiol. 2012;59(1):36–41. doi: 10.1016/j.jjcc.2011.09.003. PubMed DOI

Maheshwari S, et al. An automated algorithm for online detection of fragmented QRS and identification of its various morphologies. J. R. Soc. Interface. 2013;10(89):20130761. doi: 10.1098/rsif.2013.0761. PubMed DOI PMC

Haukilahti MAE, Eranti A, Kenttä T, Huikuri HV. QRS fragmentation patterns representing myocardial scar need to be separated from benign normal variants: hypotheses and proposal for morphology based classification. Front. Physiol. 2016;7:653. doi: 10.3389/fphys.2016.00653. PubMed DOI PMC

Malik M. Electrocardiographic smoke signals of fragmented QRS complex. J. Cardiovasc. Electrophysiol. 2013;24(11):1267–1270. doi: 10.1111/jce.12226. PubMed DOI

Bono V, et al. Development of an automated updated selvester QRS scoring system using SWT-based QRS fractionation detection and classification. IEEE J. Biomed. Health Inform. 2013;18(1):193–204. doi: 10.1109/JBHI.2013.2263311. PubMed DOI

Jin F, Sugavaneswaran L, Krishnan S, Chauhan VS. Quantification of fragmented QRS complex using intrinsic time-scale decomposition. Biomed. Signal Process. Control. 2017;31:513–523. doi: 10.1016/j.bspc.2016.09.015. DOI

Goovaerts G, et al. A machine-learning approach for detection and quantification of QRS fragmentation. IEEE J. Biomed. Health Inform. 2018;23(5):1980–1989. doi: 10.1109/JBHI.2018.2878492. PubMed DOI

Dragomiretskiy K, Zosso D. Variational mode decomposition. IEEE Trans. Signal Process. 2013;62(3):531–544. doi: 10.1109/TSP.2013.2288675. DOI

Bauer A, et al. Phase-rectified signal averaging detects quasi-periodicities in non-stationary data. Phys. A. 2006;364:423–434. doi: 10.1016/j.physa.2005.08.080. DOI

Goovaerts, G. et al. Risk Assessment of All-Cause Mortality in ICD Patients Using a Novel QRS Fragmentation Score. In 2018 Computing in Cardiology Conference (CinC) (Vol. 45, pp. 1-4). IEEE (2018, September).

Zabel M, et al. Clinical effectiveness of primary prevention implantable cardioverter-defibrillators: results of the EU-CERT-ICD controlled multicentre cohort study. Eur. Heart J. 2020;41(36):3437–3447. doi: 10.1093/eurheartj/ehaa226. PubMed DOI PMC

Sticherling C, et al. Sex differences in outcomes of primary prevention implantable cardioverter-defibrillator therapy: combined registry data from eleven European countries. Ep Europace. 2018;20(6):963–970. doi: 10.1093/europace/eux176. PubMed DOI PMC

Pelli A, et al. Electrocardiogram as a predictor of survival without appropriate shocks in primary prophylactic ICD patients: A retrospective multi-center study. Int. J. Cardiol. 2020;309:78–83. doi: 10.1016/j.ijcard.2020.03.024. PubMed DOI

Moeyersons J, Amoni M, Van Huffel S, Willems R, Varon C. R-DECO: an open-source Matlab based graphical user interface for the detection and correction of R-peaks. Peerj Comput. Sci. 2019;5:e226. doi: 10.7717/peerj-cs.226. PubMed DOI PMC

Beraza I, Romero I. Comparative study of algorithms for ECG segmentation. Biomed. Signal Process. Control. 2017;34:166–173. doi: 10.1016/j.bspc.2017.01.013. DOI

Martínez JP, Almeida R, Olmos S, Rocha AP, Laguna P. A wavelet-based ECG delineator: evaluation on standard databases. IEEE Trans. Biomed. Eng. 2004;51(4):570–581. doi: 10.1109/TBME.2003.821031. PubMed DOI

Demski, A., & Soria, M. L. ECG-kit: a Matlab toolbox for cardiovascular signal processing. J. Open Res. Softw., 4(1) (2016).

Villa, A., Padhy, S., Willems, R., Van Huffel, S., & Varon, C. Variational mode decomposition features for heartbeat classification. In 2018 Computing in Cardiology Conference (CinC) (Vol. 45, pp. 1–4). IEEE (2018, September).

Goovaerts, G., Vandenberk, B., Varon, C., Willems, R., & Van Huffel, S. Phase-rectified signal averaging for automatic detection of QRS fragmentation. In 2016 Computing in Cardiology Conference (CinC) (pp. 637–640). IEEE (2016, September).

Cortes C, Vapnik V. Support vector machine. Mach. Learn. 1995;20(3):273–297.

Platt J. Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Adv. Large Margin Classif. 1999;10(3):61–74.

Ozenne B, Subtil F, Maucort-Boulch D. The precision-recall curve overcame the optimism of the receiver operating characteristic curve in rare diseases. J. Clin. Epidemiol. 2015;68(8):855–859. doi: 10.1016/j.jclinepi.2015.02.010. PubMed DOI

Lundberg, S. M., & Lee, S. I. A unified approach to interpreting model predictions. Adv. Neural Inf. Process. Syst., 30 (2017).

Lundberg S, et al. Explainable machine-learning predictions for the prevention of hypoxaemia during surgery. Nat. Biomed. Eng. 2018;2(10):749–760. doi: 10.1038/s41551-018-0304-0. PubMed DOI PMC

Najít záznam

Citační ukazatele

Nahrávání dat ...

Možnosti archivace

Nahrávání dat ...