Can machine learning improve patient selection for cardiac resynchronization therapy?

Autoři: Szu-Yeu Hu aff001;  Enrico Santus aff002;  Alexander W. Forsyth aff002;  Devvrat Malhotra aff003;  Josh Haimson aff002;  Neal A. Chatterjee aff004;  Daniel B. Kramer aff005;  Regina Barzilay aff002;  James A. Tulsky aff006;  Charlotta Lindvall aff006
Působiště autorů: Department of Radiology, Masachusetts General Hospital, Boston, Massachusetts, United States of America aff001;  Department of Electrical Engineering and Computer Science, CSAIL, MIT, Cambridge, Massachusetts, United States of America aff002;  Department of Health Policy and Management, Harvard School of Public Health, Boston, Massachusetts, United States of America aff003;  Division of Cardiology, Department of Medicine, University of Washington, Seattle, Washington, United States of America aff004;  Richard A. and Susan F. Smith Center for Outcomes Research, Division of Cardiology, Beth Israel Deaconess Medical Center, Boston, Massachusetts, United States of America aff005;  Department of Psychosocial Oncology and Palliative Care, Dana-Farber Cancer Institute, Boston, Massachusetts, United States of America aff006;  Division of Palliative Medicine, Department of Medicine, Brigham and Women’s Hospital, Boston, Massachusetts, United States of America aff007
Vyšlo v časopise: PLoS ONE 14(10)
Kategorie: Research Article



Multiple clinical trials support the effectiveness of cardiac resynchronization therapy (CRT); however, optimal patient selection remains challenging due to substantial treatment heterogeneity among patients who meet the clinical practice guidelines.


To apply machine learning to create an algorithm that predicts CRT outcome using electronic health record (EHR) data avaible before the procedure.

Methods and results

We applied machine learning and natural language processing to the EHR of 990 patients who received CRT at two academic hospitals between 2004–2015. The primary outcome was reduced CRT benefit, defined as <0% improvement in left ventricular ejection fraction (LVEF) 6–18 months post-procedure or death by 18 months. Data regarding demographics, laboratory values, medications, clinical characteristics, and past health services utilization were extracted from the EHR available before the CRT procedure. Bigrams (i.e., two-word sequences) were also extracted from the clinical notes using natural language processing. Patients accrued on average 75 clinical notes (SD, 29) before the procedure including data not captured anywhere else in the EHR. A machine learning model was built using 80% of the patient sample (training and validation dataset), and tested on a held-out 20% patient sample (test dataset). Among 990 patients receiving CRT the mean age was 71.6 (SD, 11.8), 78.1% were male, 87.2% non-Hispanic white, and the mean baseline LVEF was 24.8% (SD, 7.69). Out of 990 patients, 403 (40.7%) were identified as having a reduced benefit from the CRT device (<0% LVEF improvement in 25.2%, death by 18 months in 15.6%). The final model identified 26% of these patients at a positive predictive value of 79% (model performance: Fβ (β = 0.1): 77%; recall 0.26; precision 0.79; accuracy 0.65).


A machine learning model that leveraged readily available EHR data and clinical notes identified a subset of CRT patients who may not benefit from CRT before the procedure.

Klíčová slova:

Cardiology – Coronary heart disease – Heart failure – Machine learning – Medical devices and equipment – Medical implants – Natural language processing – Semantics


1. Cazeau S, Leclercq C, Lavergne T, Walker S, Varma C, Linde C, et al. Effects of multisite biventricular pacing in patients with heart failure and intraventricular conduction delay. N Engl J Med. 2001;344(12):873–80. doi: 10.1056/NEJM200103223441202 11259720

2. Abraham WT, Fisher WG, Smith AL, Delurgio DB, Leon AR, Loh E, et al. Cardiac resynchronization in chronic heart failure. N Engl J Med. 2002;346(24):1845–53. doi: 10.1056/NEJMoa013168 12063368

3. Young JB, Abraham WT, Smith AL, Leon AR, Lieberman R, Wilkoff B, et al. Combined cardiac resynchronization and implantable cardioversion defibrillation in advanced chronic heart failure: the MIRACLE ICD Trial. Jama. 2003;289(20):2685–94. doi: 10.1001/jama.289.20.2685 12771115

4. Bristow MR, Saxon LA, Boehmer J, Krueger S, Kass DA, De Marco T, et al. Cardiac-resynchronization therapy with or without an implantable defibrillator in advanced chronic heart failure. N Engl J Med. 2004;350(21):2140–50. doi: 10.1056/NEJMoa032423 15152059

5. Cleland JGF, Daubert J-C, Erdmann E, Freemantle N, Gras D, Kappenberger L, et al. The effect of cardiac resynchronization on morbidity and mortality in heart failure. N Engl J Med. 2005;352(15):1539–49. doi: 10.1056/NEJMoa050496 15753115

6. Chatterjee NA, Singh JP. Cardiac resynchronization therapy: past, present, and future. Heart Fail Clin. 2015;11(2):287–303. doi: 10.1016/j.hfc.2014.12.007 25834976

7. Friedman DJ, Upadhyay GA, Rajabali A, Altman RK, Orencole M, Parks KA, et al. Progressive ventricular dysfunction among nonresponders to cardiac resynchronization therapy: baseline predictors and associated clinical outcomes. Hear Rhythm. 2014;11(11):1991–8.

8. Members AF, Brignole M, Auricchio A, Baron-Esquivias G, Bordachar P, Boriani G, et al. 2013 ESC Guidelines on cardiac pacing and cardiac resynchronization therapy: the Task Force on cardiac pacing and resynchronization therapy of the European Society of Cardiology (ESC). Developed in collaboration with the European Heart Rhythm Association. Eur Heart J. 2013;34(29):2281–329. doi: 10.1093/eurheartj/eht150 23801822

9. Tracy CM, Epstein AE, Darbar D, DiMarco JP, Dunbar SB, Estes NAM, et al. 2012 ACCF/AHA/HRS focused update incorporated into the ACCF/AHA/HRS 2008 guidelines for device-based therapy of cardiac rhythm abnormalities: a report of the American College of Cardiology Foundation/American Heart Association Task Force on Practice Guide. J Am Coll Cardiol. 2013;61(3):e6—e75.

10. Chung ES, Leon AR, Tavazzi L, Sun J-P, Nihoyannopoulos P, Merlino J, et al. Results of the Predictors of Response to CRT (PROSPECT) trial. echocardiography. 2008;2608:2616.

11. Szlosek DA, Ferrett J. Using machine learning and natural language processing algorithms to automate the evaluation of clinical decision support in electronic medical record systems. eGEMs. 2016;4(3).

12. Obermeyer Z, Emanuel EJ. Predicting the future—big data, machine learning, and clinical medicine. N Engl J Med. 2016;375(13):1216. doi: 10.1056/NEJMp1606181 27682033

13. Weiss S, Shin M. Infrastructure for personalized medicine at Partners HealthCare. J Pers Med. 2016;6(1):13.

14. Vanderkam D. Local Turk [Internet]. Github. 2018.

15. Databases H. Healthcare cost and utilization project (HCUP). Agency for Healthcare Research and Quality, Rockville, MD; 2008.

16. Stearns MQ, Price C, Spackman KA, Wang AY. SNOMED clinical terms: overview of the development process and project status. In: Proceedings of the AMIA Symposium. 2001. p. 662.

17. Evert S. The statistics of word cooccurrences: word pairs and collocations. 2005;

18. Mikolov T, Sutskever I, Chen K, Corrado GS, Dean J. Distributed representations of words and phrases and their compositionality. In: Advances in neural information processing systems. 2013. p. 3111–9.

19. Rehurek R, Sojka P. Software framework for topic modelling with large corpora. In: In Proceedings of the LREC 2010 Workshop on New Challenges for NLP Frameworks. 2010.

20. Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, et al. Scikit-learn: Machine learning in Python. J Mach Learn Res. 2011;12(Oct):2825–30.

21. Chen T, Guestrin C. Xgboost: A scalable tree boosting system. In: Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining.

22. Sipahi I, Carrigan TP, Rowland DY, Stambler BS, Fang JC. Impact of QRS duration on clinical event reduction with cardiac resynchronization therapy: meta-analysis of randomized controlled trials. Arch Intern Med. 2011;171(16):1454–62. doi: 10.1001/archinternmed.2011.247 21670335

23. Linde C, Abraham WT, Gold MR, Daubert JC, Tang ASL, Young JB, et al. Predictors of short-term clinical response to cardiac resynchronization therapy. Eur J Heart Fail. 2017;19(8):1056–63. doi: 10.1002/ejhf.795 28295869

24. Murdoch TB, Detsky AS. The inevitable application of big data to health care. Jama. 2013;309(13):1351–2. doi: 10.1001/jama.2013.393 23549579

25. Downing NS, Shah ND, Neiman JH, Aminawung JA, Krumholz HM, Ross JS. Participation of the elderly, women, and minorities in pivotal trials supporting 2011–2013 US Food and Drug Administration approvals. Trials. 2016;17(1):199.

26. Nordon C, Karcher H, Groenwold RHH, Ankarfeldt MZ, Pichler F, Chevrou-Severac H, et al. The “Efficacy-Effectiveness Gap”: historical background and current conceptualization. Value Heal. 2016;19(1):75–81.

27. Weng SF, Reps J, Kai J, Garibaldi JM, Qureshi N. Can machine-learning improve cardiovascular risk prediction using routine clinical data? PLoS One. 2017;12(4):e0174944. doi: 10.1371/journal.pone.0174944 28376093

28. Motwani M, Dey D, Berman DS, Germano G, Achenbach S, Al-Mallah MH, et al. Machine learning for prediction of all-cause mortality in patients with suspected coronary artery disease: a 5-year multicentre prospective registry analysis. Eur Heart J. 2016;38(7):500–7.

29. Kalscheur MM, Kipp RT, Tattersall MC, Mei C, Buhr KA, DeMets DL, et al. Machine learning algorithm predicts cardiac resynchronization therapy outcomes: lessons from the COMPANION trial. Circ Arrhythmia Electrophysiol. 2018;11(1):e005499.

30. Lindvall C, Chatterjee NA, Chang Y, Chernack B, Jackson VA, Singh JP, et al. National trends in the use of cardiac resynchronization therapy with or without implantable cardioverter-defibrillator. Circulation. 2016;133(3):273–81. doi: 10.1161/CIRCULATIONAHA.115.018830 26635400

31. Chen JH, Asch SM. Machine learning and prediction in medicine—beyond the peak of inflated expectations. N Engl J Med. 2017;376(26):2507. doi: 10.1056/NEJMp1702071 28657867

32. Carità P, Corrado E, Pontone G, Curnis A, Bontempi L, Novo G, et al. Non-responders to cardiac resynchronization therapy: Insights from multimodality imaging and electrocardiography. A brief review. International Journal of Cardiology. 2016.

33. Coppola G, Bonaccorso P, Corrado E, Ciaramitaro G, Ajello L, Nugara C, et al. The QRS narrowing index for easy and early identification of responder to cardiac resynchronization therapy. Int J Cardiol. 2014;

34. Coppola G, Ciaramitaro G, Stabile G, DOnofrio A, Palmisano P, Carità P, et al. Magnitude of QRS duration reduction after biventricular pacing identifies responders to cardiac resynchronization therapy. Int J Cardiol. 2016;

35. Cabitza F, Rasoini R, Gensini GF. Benefits and Risks of Machine Learning Decision Support Systems—Reply. JAMA. 2017;318(23):2356–7.

36. Arras L, Horn F, Montavon G, Müller K-R, Samek W. “What is relevant in a text document?”: An interpretable machine learning approach. PLoS One. 2017;12(8):e0181142. doi: 10.1371/journal.pone.0181142 28800619

Článek vyšel v časopise


2019 Číslo 10
Nejčtenější tento týden