Implementation of Machine Learning to Improve Implantable Cardioverter-Defibrillator Detection Algorithms

Main Article Content

Samuel Newell, MS Trenton Callaway, BBME Selçuk Adabag, MD, MS, FHRS Elena G. Tolkacheva, PhD

Abstract

Background: Sudden cardiac death is a leading cause of death in the US and globally. Implantable cardioverter-defibrillators (ICD) prevent this through electrical therapy, but inappropriate therapy for non-life threatening heart rhythms remains pervasive.


Objective: The goal of this study was to improve upon current ICD discrimination algorithms by using supervised machine learning techniques on an annotated database of ICD electrograms (EGM) preceding therapy to discriminate between appropriate (App) or inappropriate (InApp) therapies.


Methods: A total of 54 EGMs of therapy events adjudicated by cardiologists were digitized from 49 cases. The signals were analyzed within either a single long window, or four short overlapping windows preceding therapy. The discrimination between App and InApp therapies was done using EGMs recorded over specific windows by separately calculating RR-based and nonlinear dynamic (NLD) based metrics, and creating RR- and NLD-scores, respectively. Linear and quadratic discriminant analysis (LDA and QDA) were then used on the obtained RR- and NLD-scores to predict the App or InApp therapy. These results were then compared to the App and InApp designation by cardiologists. Error rates based on incorrect classifications were used to evaluate the performance of both techniques.


Results: We demonstrated that the optimal windows for LDA and QDA can both greatly improve upon modern error rates, with our QDA error going as low as nearly 2% when using an optimal window, as compared to the errors up to 25% found in recent studies. Despite QDA having a lower overall error across all windows, the QDA error came mostly from more dangerous false negatives, whereas the majority of LDA error came from less dangerous false positives.


Conclusions: This novel strategy shows promise for use in retrospective discrimination of inappropriate and appropriate ICD therapy events and could improve real time decision making algorithms in ICDs. Additional studies should be completed to assess its utility in real time decision making and case adjudication.

Article Details

How to Cite
NEWELL, Samuel et al. Implementation of Machine Learning to Improve Implantable Cardioverter-Defibrillator Detection Algorithms. Medical Research Archives, [S.l.], v. 12, n. 10, oct. 2024. ISSN 2375-1924. Available at: <https://esmed.org/MRA/mra/article/view/5913>. Date accessed: 05 dec. 2024. doi: https://doi.org/10.18103/mra.v12i10.5913.
Section
Research Articles

References

1. N. Srinivasan and R. Schilling, "Sudden Cardiac Death and Arrhythmias," Arrhythmia and Electrophysiology Review, vol. 7, no. 2, pp. 111-7, 2018.

2. Adabag, A. S., Roger, V. L., Gersh, B. J., & Luepker, R. V. (2010). Sudden cardiac death: epidemiology and risk factors. Nature Reviews Cardiology, 7(4), 216–225. https://doi.org/10.1038/nrcardio.2010.3

3. Adabag, S., & Langsetmo, L. (2020). Sudden cardiac death risk prediction in heart failure with preserved ejection fraction. Heart Rhythm, 17(3), 358–364. https://doi.org/10.1016/j.hrthm.2019.12.009

4. Adabag, S., Hodgson, L., Garcia, S., Anand, V., Frascone, R., Conterato, M., Lick, C., Wesley, K., Mahoney, B., & Yannopoulos, D. (2017). Outcomes of sudden cardiac arrest in a state-wide integrated resuscitation program: Results from the Minnesota Resuscitation Consortium. Resuscitation, 110, 95–100. https://doi.org/10.1016/j.resuscitation.2016.10.029

5. N. Ghosh, I. Mangat, S. O'Donnell, A. Pinter, V. Korley, C. Lane and P. Dorian, "Outcomes in heart failure patients referred for consideration of implantable cardioverter defibrillator for primary prophylaxis of sudden cardiac death: What are the risks of waiting?," Can J Cardiol., pp. e342-e346, 2009.

6. B. Schrage, A. Uijl, L. Benson, D. Westermann, M. Stahlberg, D. Stolfo, C. Linde, F. Braunschweig and G. Savarese, "Association Between Use of Primary-Prevention Implantable Cardioverter-Defibrillators and Mortality in Patients With Heart Failure," Circulation, pp. 1530-1539, 2019.

7. Moss, A. J., Zareba, W., Hall, W. J., Klein, H., Wilber, D. J., Cannom, D. S., Daubert, J. P., Higgins, S. L., Brown, M. W., & Andrews, M. L. (2002). Prophylactic Implantation of a Defibrillator in Patients with Myocardial Infarction and Reduced Ejection Fraction. The New England Journal of Medicine, 346(12), 877–883.
https://doi.org/10.1056/NEJMoa013474

8. Bardy, G. H., Lee, K. L., Mark, D. B., Poole, J. E., Packer, D. L., Boineau, R., Domanski, M., Troutman, C., Anderson, J., Johnson, G., McNulty, S. E., Clapp-Channing, N., Davidson-Ray, L. D., Fraulo, E. S., Fishbein, D. P., Luceri, R. M., & Ip, J. H. (2005). Amiodarone or an Implantable Cardioverter–Defibrillator for Congestive Heart Failure. The New England Journal of Medicine, 352(3), 225–237. https://doi.org/10.1056/NEJMoa043399

9. Anantha Narayanan, M., Vakil, K., Reddy, Y. N., Baskaran, J., Deshmukh, A., Benditt, D. G., & Adabag, S. (2017). Efficacy of Implantable Cardioverter-Defibrillator Therapy in Patients With Nonischemic Cardiomyopathy: A Systematic Review and Meta-Analysis of Randomized Controlled Trials. JACC. Clinical Electrophysiology, 3(9), 962–970. https://doi.org/10.1016/j.jacep.2017.02.006

10. Adabag, S., Patton, K. K., Buxton, A. E., Rector, T. S., Ensrud, K. E., Vakil, K., Levy, W. C., & Poole, J. E. (2017). Association of Implantable Cardioverter Defibrillators With Survival in Patients With and Without Improved Ejection Fraction: Secondary Analysis of the Sudden Cardiac Death in Heart Failure Trial. JAMA Cardiology, 2(7), 767–774. https://doi.org/10.1001/jamacardio.2017.1413

11. A. Auricchio, E. Schloss, T. Kurita, A. Meijer, B. Gerritse, S. Zweibel, ... and L. Sterns, "Low inappropriate shock rates in patients with single- and dual/triple-chamber implantable cardioverter-defibrillators using a novel suite of detection algorithms: PainFree SST trial primary results," Heart Rhythm, 2015.

12. Moss, A. J., Schuger, C., Beck, C. A., Brown, M. W., Cannom, D. S., Daubert, J. P., Estes, N. A. M., Greenberg, H., Hall, W. J., Huang, D. T., Kautzner, J., Klein, H., McNitt, S., Olshansky, B., Shoda, M., Wilber, D., & Zareba, W. (2012). Reduction in Inappropriate Therapy and Mortality through ICD Programming. The New England Journal of Medicine, 367(24), 2275–2283. https://doi.org/10.1056/NEJMoa1211107

13. R. Passman, H. Subacius, B. Ruo, A. Schaechter, A. Howard, S. Sears and A. Kadish, "Implantable Cardioverter Defibrillators and Quality of Life: Results From the Defibrillators in Nonischemic Cardiomyopathy Treatment Evaluation Study," Arch Intern Med., pp. 2226-2232, 2007.

14. E. Schron, D. Exner, Q. Yao, L. Jenkins, J. Steinberg, J. Cook, ... and J. Powell, "Quality of life in the antiarrhythmics versus implantable defibrillators trial: impact of therapy and influence of adverse symptoms and defibrillator shocks," Circulation, pp. 589-594, 2002. Rep. 2016 Aug 17;2(6):478-483. doi: 10.1016/j.hrcr.2016.06.006. PMID: 28491741; PMCID: PMC5419980.

15. Ellenbogen, K., & Kaszala, K. (2020). Cardiac pacing and ICDs (Sixth ed.). Chichester, West Sussex: John Wiley & Sons. pp. 350-352.

16. Al-Khatib SM, Belbase S, Sauro D, Brock G, Brink K, Jackson KP. inappropriate shocks in a patient with a subcutaneous implantable cardioverter-defibrillator. HeartRhythm Case

17. Singh, S. N., Wininger, M., Raitt, M., Adabag, S., Moore, H., Rottman, J. N., Scrymgeour, A., Zhang, J., Zheng, K., Guarino, P., Kyriakides, T. C., Johnson, G., Williams, A., Beed, A., MacMurdy, K., & Saavedra, P. (2024). Efficacy and safety of implantable cardioverter-defibrillator implantation in the elderly—The I-70 Study: A randomized clinical trial. Heart Rhythm O2, 5(6), 365–373. https://doi.org/10.1016/j.hroo.2024.04.010

18. Maheshwari, A., Norby, F. L., Soliman, E. Z., Alraies, M. C., Adabag, S., O’neal, W. T., Alonso, A., & Chen, L. Y. (2017). Relation of Prolonged P-wave Duration to Risk of Sudden Cardiac Death in the General Population (From the Atherosclerosis Risk in Communities Study). The American Journal of Cardiology, 119(9), 1302–1306.
https://doi.org/10.1016/j.amjcard.2017.01.012

19. S. Arunachalam, S. Kapa, S. Mulpuru, P. Friedman and E. G. Tolkacheva, "Improved Multiscale Entropy Technique with Nearest-Neighbor Moving-Average Kernel for Nonlinear and Nonstationary Short-Time Biomedical Signal Analysis," Journal of Healthcare Engineering, 2018.

20. V. Ravikumar, E. Annoni, S. Mulpuru, H. Roukoz and E. Tolkacheva, "Evaluation of multiscale frequency approach for visualizing rotors in patients with atrial fibrillation," Proceedings of IEEE EMBC, 2018.

21. S. Arunachalam, E. Annoni, S. Mulpuru, P. Friedman and E. Tolkacheva, "Novel Multiscale Frequency Approach to Identify the Pivot Point of the Rotor," Journal of Medical Devices, vol. 10, 2016.

22. C. Shannon, "A mathematical theory of communication," Bell System Technical Journal, vol. 27, no. 3, pp. 379-423, 1948.

23. classify. Classify observations using discriminant analysis - MATLAB. (n.d.).
https://www.mathworks.com/help/stats/classify.html

24. M. Gold, P. Lambiase, M. El-Chami, K. Reinoud, J. Aasbo, M. Bongiorni, ... and L. Boersma, "Primary Results From the Understanding Outcomes With the S-ICD in Primary Prevention Patients With Low Ejection Fraction (UNTOUCHED) Trial," Circulation, pp. 7-17, 2021.