Ventricular geometry–regularized QRSd predicts cardiac resynchronization therapy response: machine learning from crosstalk between electrocardiography and echocardiography

  • Juan Lei
  • Yi Grace Wang
  • Luna Bhatta
  • Jamal Ahmed
  • Dali Fan
  • Jingfeng WangEmail author
  • Kan LiuEmail author
Original Paper


Up to one-third of patients selected by current guidelines do not respond to cardiac resynchronization therapy (CRT), the aim of this study was to find out novel analytical approaches to improve pre-implantation CRT response prediction. Among 31 pre-implantation features of clinical, laboratory, electrocardiography (ECG), and echocardiography variables in a consecutive cohort of patients receiving a first-time CRT device (CRT-pacemaker or CRT-defibrillator), we developed a machine learning (ML) model with three classification algorithms (support vector machines (SVM), K nearest neighbors, and random subspaces) with the best features combination to predict CRT response. Three categorical variables, left bundle branch block (LBBB), nonischemic cardiomyopathy, and female gender, were independently associated with CRT responses. Among continuous variables, including septal wall thickness, posterior wall thickness, and relative wall thickness (RWT), could regularize ECG QRS duration (QRSd) and significantly enhance the correlation between QRSd and CRT response. The 3 ML algorithms in a total of 38 features combinations constantly recognized that the features combined with QRSd/RWT outperformed the combinations without it. For each of three algorithms, the triplet feature combination of QRSd/RWT, LBBB, and nonischemic cardiomyopathy repeatedly increased the classification rate more than 8%. The best performance for CRT response prediction occurred with SVM model, which proposed actual QRSd/RWT values that favored CRT responses in patients both with and without LBBB. Lower QRSd/RWT values were required for CRT responses in patients with ischemic cardiomyopathy compared to those with non-ischemic cardiomyopathy. ML from ventricular remodeling characteristics–regularized QRSd improves CRT response prediction.


Cardiac resynchronization therapy QRS duration Machine learning Classification Ventricular geometric characteristics 


Compliance with ethical standards

Conflict of interest

The authors report no conflicts of interest in this study.


  1. 1.
    Goldenberg I, Kutyifa V, Klein HU et al (2014) Survival with cardiac-resynchronization therapy in mild heart failure. N Engl J Med 370:1694–1701. CrossRefGoogle Scholar
  2. 2.
    Hunt SA, (2005) ACC/AHA 2005 guideline update for the diagnosis and management of chronic heart failure in the adult: a report of the American College of Cardiology/American Heart Association task force on practice guidelines (writing committee to update the 2001 guidelines for the evaluation and management of heart failure). J Am Coll Cardiol 46:e1–e82. CrossRefGoogle Scholar
  3. 3.
    Cleland JG, Freemantle N, Erdmann E et al (2012) Long-term mortality with cardiac resynchronization therapy in the cardiac resynchronization-heart failure (CARE-HF) trial. Eur J Heart Fail 14:628–634. CrossRefGoogle Scholar
  4. 4.
    Manlucu J, Tang AS (2014) Whom should I refer in 2014 for cardiac resynchronization? Can J Cardiol 30:675–678. CrossRefGoogle Scholar
  5. 5.
    Yancy CW, Jessup M, Bozkurt B et al (2013) 2013 ACCF/AHA guideline for the management of heart failure: a report of the American College of Cardiology Foundation/American Heart Association task force on practice guidelines. Circulation 128:1810–1852. CrossRefGoogle Scholar
  6. 6.
    Ponikowski P, Voors AA, Anker SD, et al (2016) 2016 ESC guidelines for the diagnosis and treatment of acute and chronic heart failure: the task force for the diagnosis and treatment of acute and chronic heart failure of the European Society of Cardiology (ESC) developed with the special contribution of the Heart Failure Association (HFA) of the ESC. Eur Heart J 37:2129–2200. CrossRefGoogle Scholar
  7. 7.
    Varma N, Manne M, Nguyen D et al (2014) Probability and magnitude of response to cardiac resynchronization therapy according to QRS duration and gender in nonischemic cardiomyopathy and LBBB. Heart Rhythm 11:1139–1147. CrossRefGoogle Scholar
  8. 8.
    Yancy CW, McMurray JJ (2013) ECG—still the best for selecting patients for CRT. N Engl J Med 369:1463–1464. CrossRefGoogle Scholar
  9. 9.
    Bleeker GB, Schalij MJ, Molhoek SG et al (2004) Relationship between QRS duration and left ventricular dyssynchrony in patients with end-stage heart failure. J Cardiovasc Electrophysiol 15:544–549. CrossRefGoogle Scholar
  10. 10.
    Bishop CM (2006) Pattern recognition and machine learning (information science and statistics). Springer, New YorkGoogle Scholar
  11. 11.
    Obermeyer Z, Emanuel EJ (2016) Predicting the future—big data, machine learning, and clinical medicine. N Engl J Med 375:1216–1219. CrossRefGoogle Scholar
  12. 12.
    Sengupta PP, Huang YM, Bansal M et al (2016) Cognitive machine-learning algorithm for cardiac imaging: a pilot study for differentiating constrictive pericarditis from restrictive cardiomyopathy. Circ Cardiovasc Imaging 9:e004330. CrossRefGoogle Scholar
  13. 13.
    Ellenbogen KA, Huizar JF (2012) Foreseeing super-response to cardiac resynchronization therapy: a perspective for clinicians. J Am Coll Cardiol 59:2374–2377. CrossRefGoogle Scholar
  14. 14.
    Felker GM, Shaw LK, O’Connor CM (2002) A standardized definition of ischemic cardiomyopathy for use in clinical research. J Am Coll Cardiol 39:210–218. CrossRefGoogle Scholar
  15. 15.
    Gold MR, Thebault C, Linde C et al (2012) The effect of QRS duration and morphology on cardiac resynchronization therapy outcomes in mild heart failure: results from the resynchronization Reverses remodeling in systolic left ventricular dysfunction (REVERSE) study. Circulation 126:822–829. CrossRefGoogle Scholar
  16. 16.
    Wang YG, Wu HT, Daubechies I et al (2015) Automated J wave detection from digital 12-lead electrocardiogram. J Electrocardiol 48:21–28. CrossRefGoogle Scholar
  17. 17.
    Surawicz B, Childers R, Deal BJ et al (2009) AHA/ACCF/HRS recommendations for the standardization and interpretation of the electrocardiogram, part III: intraventricular conduction disturbances a scientific statement from the American Heart Association Electrocardiography and Arrhythmias Committee, Council on Clinical Cardiology; the American College of Cardiology Foundation; and the Heart Rhythm Society endorsed by the International Society for Computerized Electrocardiology. J Am Coll Cardiol 53:976–981. CrossRefGoogle Scholar
  18. 18.
    Lang RM, Bierig M, Devereux RB et al (2005) Recommendations for chamber quantification: a report from the American Society of Echocardiography’s Guidelines and Standards Committee and the Chamber Quantification Writing Group, developed in conjunction with the European Association of Echocardiography, a branch of the European Society of Cardiology. J Am Soc Echocardiogr 18:1440–1463. CrossRefGoogle Scholar
  19. 19.
    Biton Y, Goldenberg I, Kutyifa V et al (2016) Relative wall thickness and the risk for ventricular tachyarrhythmias in patients with left ventricular dysfunction. J Am Coll Cardiol 67:303–312. CrossRefGoogle Scholar
  20. 20.
    Devereux RB, Alonso DR, Lutas EM et al (1986) Echocardiographic assessment of left ventricular hypertrophy: comparison to necropsy findings. Am J Cardiol 57:450–458. CrossRefGoogle Scholar
  21. 21.
    Nagueh SF, Appleton CP, Gillebert TC et al (2009) Recommendations for the evaluation of left ventricular diastolic function by echocardiography. J Am Soc Echocardiogr 22:107–133. CrossRefGoogle Scholar
  22. 22.
    Lei J, Dhamoon AS, Wang JF et al (2016) Walking the tightrope: using quantitative Doppler echocardiography to optimize ventricular filling pressures in patients hospitalized for acute heart failure. Eur Heart J Acute Cardiovasc Care 5:130–140. CrossRefGoogle Scholar
  23. 23.
    Lei J, Wang JF, Voelker R et al (2014) Developing integrated echocardiographic protocol to optimize cardiac resynchronization therapy with quadripolar lead. J Am Coll Cardiol 64 (16 Supplement): C159. Google Scholar
  24. 24.
    Jansen AH, Bracke FA, van Dantzig JM et al (2006) Correlation of echo-Doppler optimization of atrioventricular delay in cardiac resynchronization therapy with invasive hemodynamics in patients with heart failure secondary to ischemic or idiopathic dilated cardiomyopathy. Am J Cardiol 97:552–557. CrossRefGoogle Scholar
  25. 25.
    Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20:273–297. Google Scholar
  26. 26.
    Cover T, Hart P (1967) Nearest neighbor pattern classification. IEEE Trans Inf Theory 13:21–27. CrossRefGoogle Scholar
  27. 27.
    Ho TK (1998) The random subspace method for constructing decision forests. IEEE Trans Pattern Anal Mach Intell 20:832–844. CrossRefGoogle Scholar
  28. 28.
    Gaasch WH, Zile MR (2011) Left ventricular structural remodeling in health and disease: with special emphasis on volume, mass, and geometry. J Am Coll Cardiol 58:1733–1740. CrossRefGoogle Scholar
  29. 29.
    Zhang Q, Fung JW, Auricchio A et al (2006) Differential change in left ventricular mass and regional wall thickness after cardiac resynchronization therapy for heart failure. Eur Heart J 27:1423–1430. CrossRefGoogle Scholar
  30. 30.
    Chan DD, Wu KC, Loring Z et al (2014) Comparison of the relation between left ventricular anatomy and QRS duration in patients with cardiomyopathy with versus without left bundle branch block. Am J Cardiol 113:1717–1722. CrossRefGoogle Scholar
  31. 31.
    Draper TS Jr, Silver JS, Gaasch WH (2015) Adverse structural remodeling of the left ventricle and ventricular arrhythmias in patients with depressed ejection fraction. J Card Fail 21:97–102. CrossRefGoogle Scholar
  32. 32.
    Gasparini M, Galimberti P (2013) Device therapy in heart failure: has CRT changed “the sickest benefit the most” to “the healthiest benefit the most?”. J Am Coll Cardiol 61:945–947. CrossRefGoogle Scholar
  33. 33.
    Adelstein EC, Saba S (2007) Scar burden by myocardial perfusion imaging predicts echocardiographic response to cardiac resynchronization therapy in ischemic cardiomyopathy. Am Heart J 153:105–112. CrossRefGoogle Scholar

Copyright information

© Springer Nature B.V. 2019

Authors and Affiliations

  1. 1.Division of Cardiology, Department of MedicineState University of New York, Upstate Medical UniversitySyracuseUSA
  2. 2.Department of CardiologySun Yat-Sen Memorial Hospital, Sun Yat-Sen UniversityGuangzhouChina
  3. 3.Department of MathematicsCalifornia State University Dominguez HillsCarsonUSA
  4. 4.Division of Cardiology, Department of MedicineUniversity of CaliforniaDavisUSA
  5. 5.Division of Cardiology, Department of MedicineUniversity of IowaIowa CityUSA

Personalised recommendations