Skip to main content
SpringerLink
Log in

Multivariate ensemble classification for the prediction of symptoms in patients with Brugada syndrome

  • Original Article
  • Published:
Medical & Biological Engineering & Computing Aims and scope Submit manuscript

Abstract

Identification of asymptomatic patients at higher risk for suffering cardiac events remains controversial and challenging in Brugada syndrome (BS). In this work, we proposed an ECG-based classifier to predict BS-related symptoms, by merging the most predictive electrophysiological features derived from the ventricular depolarization and repolarization periods, along with autonomic-related markers. The initial feature space included local and dynamic ECG markers, assessed during a physical exercise test performed in 110 BS patients (25 symptomatic). Morphological, temporal and spatial properties quantifying the ECG dynamic response to exercise and recovery were considered. Our model was obtained by proposing a two-stage feature selection process that combined a resampled-based regularization approach with a wrapper model assessment for balancing, simplicity and performance. For the classification step, an ensemble was constructed by several logistic regression base classifiers, whose outputs were fused using a performance-based weighted average. The most relevant predictors corresponded to the repolarization interval, followed by two autonomic markers and two other makers of depolarization dynamics. Our classifier allowed for the identification of novel symptom-related markers from autonomic and dynamic ECG responses during exercise testing, suggesting the need for multifactorial risk stratification approaches in order to predict future cardiac events in asymptomatic BS patients.

Pipeline for feature selection and predictive modeling of symptoms in Brugada syndrome

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

Similar content being viewed by others

References

  1. Acar B, Yi G, Hnatkova K, Malik M (1999) Spatial, temporal and wavefront direction characteristics of 12-lead T-wave morphology. Med Biol Eng Comput 37(5):574–584. https://doi.org/10.1007/BF02513351

    Article  CAS  Google Scholar 

  2. Béhar N, Petit B, Probst V, Sacher F, Kervio G, Mansourati J, Bru P, Hernandez A, Mabo P (2017) Heart rate variability and repolarization characteristics in symptomatic and asymptomatic Brugada syndrome. Europace 19(10):1730–1736. https://doi.org/10.1093/europace/euw224

    PubMed  Google Scholar 

  3. Calvo M, Romero D, Le Rolle V, Béhar N, Gomis P, Mabo P, Hernández AI (2018) Multivariate classification of Brugada syndrome patients based on autonomic response to exercise testing. PLos ONE 13(5). https://doi.org/10.1371/journal.pone.0197367

  4. Cole CR, Blackstone EH, Pashkow FJ, Snader CE, Lauer MS (1999) Heart-rate recovery immediately after exercise as a predictor of mortality. N Engl J Med 341(18):1351–1357. https://doi.org/10.1056/NEJM199910283411804

    Article  CAS  Google Scholar 

  5. Dumont J, Hernández AI, Carrault G (2010) Improving ECG beats delineation with an evolutionary optimization process. IEEE Trans Biomed Eng 57(3):607–615. https://doi.org/10.1109/TBME.2008.2002157

    Article  Google Scholar 

  6. Edenbrandt L, Pahlm O (1988) Vectorcardiogram synthesized from a 12-lead ECG: superiority of the inverse Dower matrix. J Electrocardiol 21(4):361–367. https://doi.org/10.1016/0022-0736(88)90113-6

    Article  CAS  Google Scholar 

  7. Kawazoe H, Nakano Y, Ochi H, Takagi M, Hayashi Y, Uchimura Y, Tokuyama T, Watanabe Y, Matsumura H, Tomomori S, Sairaku A, Suenari K, Awazu A, Miwa Y, Soejima K, Chayama K, Kihara Y (2016) Risk stratification of ventricular fibrillation in Brugada syndrome using noninvasive scoring methods. Heart Rhythm 13(10):1947–1954. https://doi.org/10.1016/j.hrthm.2016.07.009

    Article  Google Scholar 

  8. Kawazoe H, Nakano Y, Ochi H, Takagi M, Hayashi Y, Uchimura Y, Tokuyama T, Watanabe Y, Matsumura H, Tomomori S, Sairaku A, Suenari K, Awazu A, Miwa Y, Soejima K, Chayama K, Kihara Y (2016) Risk stratification of ventricular fibrillation in Brugada syndrome using noninvasive scoring methods. Heart Rhythm 13(10):1947–1954. https://doi.org/10.1016/j.hrthm.2016.07.009

    Article  Google Scholar 

  9. Kohavi R, John GH (1997) Wrappers for feature subset selection. Artif Intell 97(1-2):273–324. https://doi.org/10.1016/s0004-3702(97)00043-x

    Article  Google Scholar 

  10. Kuncheva LI (2014) Combining pattern classifiers: methods and algorithms: 2nd Edn, pp 9781118315231. https://doi.org/10.1002/9781118914564

  11. Laguna P, Martinez Cortes JP, Pueyo E (2016) Techniques for ventricular repolarization instability assessment from the ECG. https://doi.org/10.1109/JPROC.2015.2500501

  12. Langley P, Di Bernardo D, Murray A (2002) Quantification of T wave shape changes following exercise. PACE - Pacing Clin Electrophysiolx 25(8):1230–1234. https://doi.org/10.1046/j.1460-9592.2002.01230.x

    Article  Google Scholar 

  13. Makimoto H, Nakagawa E, Takaki H, Yamada Y, Okamura H, Noda T, Satomi K, Suyama K, Aihara N, Kurita T, Kamakura S, Shimizu W (2010) Augmented ST-segment elevation during recovery from exercise predicts cardiac events in patients with brugada syndrome. J Am Coll Cardiol 56(19):1576–1584. https://doi.org/10.1016/j.jacc.2010.06.033

    Article  Google Scholar 

  14. Meijborg VM, Chauveau S, Janse MJ, Anyukhovsky EP, Danilo PR, Rosen MR, Opthof T, Coronel R (2015) Interventricular dispersion in repolarization causes bifid T waves in dogs with dofetilide-induced long QT syndrome. Heart Rhythm 12(6):1343–1351. https://doi.org/10.1016/j.hrthm.2015.02.026

    Article  Google Scholar 

  15. Meregalli PG, Wilde AA, Tan HL (2005) Pathophysiological mechanisms of Brugada syndrome: Depolarization disorder, repolarization disorder or more? https://doi.org/10.1016/j.cardiores.2005.03.005

  16. Morita H, Fukushima-Kusano K, Nagase S, Miyaji K, Hiramatsu S, Banba K, Nishii N, Watanabe A, Kakishita M, Takenaka-Morita S, Nakamura K, Saito H, Emori T, Ohe T (2004) Sinus node function in patients with Brugada-type ECG. Circ J 68(5):473–476. https://doi.org/10.1253/circj.68.473

    Article  Google Scholar 

  17. Morita H, Kusano KF, Miura D, Nagase S, Nakamura K, Morita ST, Ohe T, Zipes DP, Wu J (2008) Fragmented QRS as a marker of conduction abnormality and a predictor of prognosis of Brugada syndrome. Circulation 118(17):1697–1704. https://doi.org/10.1161/CIRCULATIONAHA.108.770917

    Article  Google Scholar 

  18. Polikar R (2006) Ensemble based systems in decision making. https://doi.org/10.1109/MCAS.2006.1688199

  19. Postema PG, van Dessel PF, Kors JA, Linnenbank AC, van Herpen G, Ritsema van Eck HJ, van Geloven N, de Bakker JM, Wilde AA, Tan HL (2010) Local depolarization abnormalities are the dominant pathophysiologic mechanism for type 1 electrocardiogram in brugada syndrome. a study of electrocardiograms, vectorcardiograms, and body surface potential maps during ajmaline provocation. J Am Coll Cardiol 55(8):789–797. https://doi.org/10.1016/j.jacc.2009.11.033

    Article  Google Scholar 

  20. Postema PG, van Dessel PF, Kors JA, Linnenbank AC, van Herpen G, Ritsema van Eck HJ, van Geloven N, de Bakker JM, Wilde AA, Tan HL (2010) Local depolarization abnormalities are the dominant pathophysiologic mechanism for type 1 electrocardiogram in brugada syndrome. a study of electrocardiograms, vectorcardiograms, and body surface potential maps during ajmaline provocation. J Am Coll Cardiol 55(8):789–797. https://doi.org/10.1016/j.jacc.2009.11.033

    Article  Google Scholar 

  21. Postema PG, Wilde AA (2016) Risk stratification in Brugada syndrome: Where is the finish line? https://doi.org/10.1016/j.hrthm.2016.08.008

  22. Priori SG, Blomström-Lundqvist C, Mazzanti A, Bloma N, Borggrefe M, Camm J, Elliott PM, Fitzsimons D, Hatala R, Hindricks G, Kirchhof P, Kjeldsen K, Kuck KH, Hernandez-Madrid A, Nikolaou N, Norekvål TM, Spaulding C, Van Veldhuisen DJ, Kolh P, Lip GY, Agewall S, Barón-Esquivias G, Boriani G, Budts W, Bueno H, Capodanno D, Carerj S, Crespo-Leiro MG, Czerny M, Deaton C, Dobrev D, Erol Ç, Galderisi M, Gorenek B, Kriebel T, Lambiase P, Lancellotti P, Lane DA, Lang I, Manolis AJ, Morais J, Moreno J, Piepoli MF, Rutten FH, Sredniawa B, Zamorano JL, Zannad F (2015) 2015 ESC Guidelines for the management of patients with ventricular arrhythmias and the prevention of sudden cardiac death: the Task Force for the Management of Patients with Ventricular Arrhythmias and the Prevention of Sudden Cardiac Death of the European Society of Cardiology (ESC). Europace 17(11):1601–1687. https://doi.org/10.1093/europace/euv319

    PubMed  Google Scholar 

  23. Priori SG, Wilde AA, Horie M, Cho Y, Behr ER, Berul C, Blom N, Brugada J, Chiang CE, Huikuri H, Kannankeril P, Krahn A, Leenhardt A, Moss A, Schwartz PJ, Shimizu W, Tomaselli G, Tracy C, Document Reviewers, Ackerman M, Belhassen B, Estes NA, Fatkin D, Kalman J, Kaufman E, Kirchhof P, Schulze-Bahr E, Wolpert C, Vohra J, Refaat M, Etheridge SP, Campbell RM, Martin ET, Quek SC (2013) Heart Rhythm Society, European Heart Rhythm Association Asia Pacific Heart Rhythm Society: executive summary: HRS/EHRA/APHRS expert consensus statement on the diagnosis and management of patients with inherited primary arrhythmia syndromes. https://doi.org/10.1093/europace/eut272

  24. Probst V, Veltmann C, Eckardt L, Meregalli PG, Gaita F, Tan HL, Babuty D, Sacher F, Giustetto C, Schulze-Bahr E, Borggrefe M, Haissaguerre M, Mabo P, Le Marec H, Wolpert C, Wilde AA (2010) Long-term prognosis of patients diagnosed with brugada syndrome: results from the finger brugada syndrome registry. Circulation 121(5):635–643. https://doi.org/10.1161/CIRCULATIONAHA.109.887026

    Article  CAS  Google Scholar 

  25. Romero D, Béhar N, Mabo P, Hernández A (2017) A biexponential approach for assessing parasympathetic reactivation after submaximal exercise. In: Computing in cardiology 44:1–4. https://doi.org/10.22489/CinC.2017.306-390

  26. Romero D, Ringborn M, Laguna P, Pahlm O, Pueyo E (2011) Depolarization changes during acute myocardial ischemia by evaluation of QRS slopes: Standard lead and vectorial approach. IEEE Trans Biomed Eng 58(1):110–120. https://doi.org/10.1109/TBME.2010.2076385

    Article  Google Scholar 

  27. Romero D, Ringborn M, Laguna P, Pueyo E (2013) Detection and quantification of acute myocardial ischemia by morphologic evaluation of QRS changes by an angle-based method. J Electrocardiol 46:204–214. https://doi.org/10.1016/j.jelectrocard.2013.02.014

  28. Sacher F, Probst V, Maury P, Babuty D, Mansourati J, Komatsu Y, Marquie C, Rosa A, Diallo A, Cassagneau R, Loizeau C, Martins R, Field ME, Derval N, Miyazaki S, Denis A, Nogami A, Ritter P, Gourraud JB, Ploux S, Rollin A, Zemmoura A, Lamaison D, Bordachar P, Pierre B, Jais P, Pasquic JL, Hocini M, Legal F, Defaye P, Boveda S, Iesaka Y, Mabo P, Haissaguerre M (2013) Outcome after implantation of a Cardioverter-Defibrillator in patients with brugada syndrome a multicenter Study-Part 2. Circulation 128(16):1739–1747. https://doi.org/10.1161/CIRCULATIONAHA.113.001941

    Article  Google Scholar 

  29. Tan HL, Amin AS, De Groot EA, Ruijter JM, Wilde AA (2009) Exercise-induced ECG changes in brugada syndrome. Circul Arrhythm Electrophysiol 2(5):531–539. https://doi.org/10.1161/CIRCEP.109.862441

    Article  Google Scholar 

  30. Tokioka K, Kusano KF, Morita H, Miura D, Nishii N, Nagase S, Nakamura K, Kohno K, Ito H, Ohe T (2014) Electrocardiographic parameters and fatal arrhythmic events in patients with brugada syndrome: combination of depolarization and repolarization abnormalities. J Am Coll Cardiol 63(20):2131–2138. https://doi.org/10.1016/j.jacc.2014.01.072

    Article  Google Scholar 

  31. Zou H, Hastie T (2005) Regularization and variable selection via the elastic net. J R Stat Soc Ser B: Stat Methodol 67(2):301–320. https://doi.org/10.1111/j.1467-9868.2005.00503.x

    Article  Google Scholar 

Download references

Funding

This work was partly supported by a grant of the French Ministry of Health (Programme Hospitalier de Recherche Clinique - PHRC Regional). D. Romero acknowledges the financial support of the Fondation Lefoulon-Delalande, Institut de France, France. M. Calvo acknowledges the financial support of the social program funded by CaixaBank, Spain.

Author information

Authors and Affiliations

  1. Institute for Bioengineering of Catalonia (IBEC), Campus Besòs EEBE-UPC, Ave. E. Maristany 16, Building C, L5.3, Barcelona, E-08019, Spain

    Daniel Romero & Mireia Calvo

  2. CHU Rennes, Inserm, University of Rennes, LTSI - UMR 1099, F-35000, Rennes, France

    Virginie Le Rolle, Nathalie Béhar, Phillipe Mabo & Alfredo Hernández

Authors
  1. Daniel Romero
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mireia Calvo
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Virginie Le Rolle
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Nathalie Béhar
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Phillipe Mabo
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Alfredo Hernández
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Conceptualization: Daniel Romero, Alfredo Hernández. Methodology: Daniel Romero, Alfredo Hernández. Formal analysis and investigation: Daniel Romero, Mireia Calvo, Virginie Le Rolle, Nathalie Béhar, Philippe Mabo, Alfredo Hernández. Software and visualization: Daniel Romero. Writing—original draft preparation: Daniel Romero. Writing—review and editing: Daniel Romero, Mireia Calvo, Virginie Le Rolle, Nathalie Béhar, Philippe Mabo, Alfredo Hernández. Funding acquisition: Daniel Romero, Alfredo Hernández, Philippe Mabo. Resources: Nathalie Béhar, Philippe Mabo, Alfredo Hernández. Supervision: Philippe Mabo, Alfredo Hernández.

Corresponding author

Correspondence to Alfredo Hernández.

Ethics declarations

Conflict of interest

The authors declare no competing interests.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Romero, D., Calvo, M., Le Rolle, V. et al. Multivariate ensemble classification for the prediction of symptoms in patients with Brugada syndrome. Med Biol Eng Comput 60, 81–94 (2022). https://doi.org/10.1007/s11517-021-02448-1

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11517-021-02448-1

Keywords

Search

Navigation