Automatic diagnosis of the 12-lead ECG using a deep neural network

Abstract

The role of automatic electrocardiogram (ECG) analysis in clinical practice is limited by the accuracy of existing models. Deep Neural Networks (DNNs) are models composed of stacked transformations that learn tasks by examples. This technology has recently achieved striking success in a variety of task and there are great expectations on how it might improve clinical practice. Here we present a DNN model trained in a dataset with more than 2 million labeled exams analyzed by the Telehealth Network of Minas Gerais and collected under the scope of the CODE (Clinical Outcomes in Digital Electrocardiology) study. The DNN outperform cardiology resident medical doctors in recognizing 6 types of abnormalities in 12-lead ECG recordings, with F1 scores above 80% and specificity over 99%. These results indicate ECG analysis based on DNNs, previously studied in a single-lead setup, generalizes well to 12-lead exams, taking the technology closer to the standard clinical practice.

Full text

Its licence does not allow us to show the full text. Read it at PubMed Central:

References 54

1. 1.
   Global, regional, and national age-sex-specific mortality for 282 causes of death in 195 countries and territories, 1980–2017: a systematic analysis for the Global Burden of Disease Study 2017 · 2018

   No notice
2. 2.

   Willems JL, et al. Testing the performance of ECG computer programs: the CSE diagnostic pilot study. J. Electrocardiol. 1987;20(Suppl):73-77.

   Not in our library

3. 3.

   Schläpfer J, Wellens HJ. Computer-interpreted electrocardiograms: benefits and limitations. J. Am. Coll. Cardiol. 2017;70:1183.

   Not in our library10.1016/j.jacc.2017.07.723

4. 4.

   Willems JL, et al. The diagnostic performance of computer programs for the interpretation of electrocardiograms. N. Engl. J. Med. 1991;325:1767-1773.

   Not in our library10.1056/nejm199112193252503

5. 5.

   Shah AP, Rubin SA. Errors in the computerized electrocardiogram interpretation of cardiac rhythm. J. Electrocardiol. 2007;40:385-390.

   Not in our library10.1016/j.jelectrocard.2007.03.008

6. 6.

   Estes NAM. Computerized interpretation of ECGs: supplement not a substitute. Circulation. Arrhythmia Electrophysiol. 2013;6:2-4.

   Not in our library10.1161/circep.111.000097

7. 7.

   Krizhevsky, A., Sutskever, I. & Hinton, G. E. Imagenet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems 1097–1105 (Curran Associates, Inc,. 2012).

   Not in our library

8. 8.

   Hinton G, et al. Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process. Mag. 2012;29:82-97.

   Not in our library10.1109/msp.2012.2205597

9. 9.

   Stead WW. Clinical implications and challenges of artificial intelligence and deep learning. JAMA. 2018;320:1107-1108.

   Not in our library10.1001/jama.2018.11029

10. 10.

    Naylor C. On the prospects for a (deep) learning health care system. JAMA. 2018;320:1099-1100.

    Not in our library10.1001/jama.2018.11103

11. 11.

    Hinton G. Deep learning—a technology with the potential to transform health care. JAMA. 2018;320:1101-1102.

    Not in our library10.1001/jama.2018.11100

12. 12.

    Bejnordi BE, et al. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. JAMA. 2017;318:2199.

    Not in our library10.1001/jama.2017.14585

13. 13.

    De Fauw J, et al. Clinically applicable deep learning for diagnosis and referral in retinal disease. Nat. Med. 2018;24:1342-1350.

    Not in our library10.1038/s41591-018-0107-6

14. 14.

    Beck EJ, Gill W, De Lay PR. Protecting the confidentiality and security of personal health information in low- and middle-income countries in the era of SDGs and Big Data. Glob. Health Action. 2016;9:32089.

    Not in our library10.3402/gha.v9.32089

15. 15.

    Hannun AY, et al. Cardiologist-level arrhythmia detection and classification in ambulatory electrocardiograms using a deep neural network. Nat. Med. 2019;25:65-69.

    Not in our library10.1038/s41591-018-0268-3

16. 16.

    Clifford GD, et al. AF classification from a short single lead ECG recording: the PhysioNet/Computing in Cardiology Challenge 2017. Comput. Cardiol. 2017;44:1-4.

    Not in our library10.22489/cinc.2017.065-469

17. 17.

    Mant J, et al. Accuracy of diagnosing atrial fibrillation on electrocardiogram by primary care practitioners and interpretative diagnostic software: analysis of data from screening for atrial fibrillation in the elderly (SAFE) trial. BMJ (Clin. Res. ed.). 2007;335:380.

    Not in our library10.1136/bmj.39227.551713.ae

18. 18.

    Veronese G, et al. Emergency physician accuracy in interpreting electrocardiograms with potential ST-segment elevation myocardial infarction: is it enough? Acute Card. Care. 2016;18:7-10.

    Not in our library10.1080/17482941.2016.1234058

19. 19.

    World Health Organization. Global Status Report on Noncommunicable Diseases 2014: Attaining the Nine Global Noncommunicable Diseases Targets; A Shared Responsibility OCLC: 907517003 (World Health Organization, Geneva, 2014).

    Not in our library

20. 20.

    Sassi R, et al. PDF-ECG in clinical practice: a model for long-term preservation of digital 12-lead ECG data. J. Electrocardiol. 2017;50:776-780.

    Not in our library10.1016/j.jelectrocard.2017.08.001

21. 21.

    Lyon A, Mincholé A, Martínez JP, Laguna P, Rodriguez B. Computational techniques for ECG analysis and interpretation in light of their contribution to medical advances. J. R. Soc. Interface. 2018;15:20170821.

    Not in our library10.1098/rsif.2017.0821

22. 22.

    Alkmim MB, et al. Improving patient access to specialized health care: the Telehealth Network of Minas Gerais, Brazil. Bull. World Health Organ. 2012;90:373-378.

    Not in our library10.2471/blt.11.099408

23. 23.

    He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In Proc. IEEE Conferenceon Computer Vision and Pattern Recognition (CVPR) 770–778 (IEEE, 2016).

    Not in our library

24. 24.

    Hong, S. et al. ENCASE: an ENsemble ClASsifiEr for ECG classification using expert features and deep neural networks. In 2017 Computingin Cardiology Conference (IEEE, 2017).

    Not in our library

25. 25.

    Kamaleswaran R, Mahajan R, Akbilgic O. A robust deep convolutional neural network for the classification of abnormal cardiac rhythm using single lead electrocardiograms of variable length. Physiological Meas. 2018;39:035006.

    Not in our library10.1088/1361-6579/aaaa9d

26. 26.

    Efron, B. & Tibshirani, R. J. An Introduction to the Bootstrap (CRC Press, 1994).

    Not in our library

27. 27.

    McNemar Q. Note on the sampling error of the difference between correlated proportions or percentages. Psychometrika. 1947;12:153-157.

    Not in our library10.1007/bf02295996

28. 28.

    Jambukia, S. H., Dabhi, V. K. & Prajapati, H. B. Classification of ECG signals using machine learning techniques: a survey. In Proc. International Conferenceon Advances in Computer Engineering and Applications (ICACEA) 714–721 (IEEE, 2015).

    Not in our library

29. 29.

    Macfarlane PW, Devine B, Clark E. The University of Glasgow (Uni-G) ECG analysis program. Comput. Cardiol. 2005;32:451-454.

    Not in our library

30. 30.

    Smith SW, et al. A deep neural network learning algorithm outperforms a conventional algorithm for emergency department electrocardiogram interpretation. J. Electrocardiol. 2019;52:88-95.

    Not in our library10.1016/j.jelectrocard.2018.11.013

31. 31.

    Cubanski D, Cyganski D, Antman EM, Feldman CL. A neural network system for detection of atrial fibrillation in ambulatory electrocardiograms. J. Cardiovasc. Electrophysiol. 1994;5:602-608.

    Not in our library10.1111/j.1540-8167.1994.tb01301.x

32. 32.

    Tripathy RK, Bhattacharyya A, Pachori RB. A novel approach for detection of myocardial infarction from ECG signals of multiple electrodes. IEEE Sens. J. 2019;19:4509-4517.

    Not in our library10.1109/jsen.2019.2896308

33. 33.

    Rubin, J., Parvaneh, S., Rahman, A., Conroy, B. & Babaeizadeh, S. Densely connected convolutional networks and signal quality analysis to detect atrial fibrillation using short single-lead ECG recordings. pp. 1–4 (Computing in Cardiology (CinC), Rennes, 2017). https://ieeexplore.ieee.org/abstract/document/8331569.

    Not in our library

34. 34.

    Acharya UR, et al. Application of deep convolutional neural network for automated detection of myocardial infarction using ECG signals. Inf. Sci. 2017;415-416:190-198.

    Not in our library10.1016/j.ins.2017.06.027

35. 35.

    Shashikumar, S. P., Shah, A. J., Clifford, G. D. & Nemati, S. Detection of paroxysmal atrial fibrillation using attention-based bidirectional recurrent neural networks. In Proc. 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD ’18, New York, NY, USA, (eds Guo, Y. & Farooq, F.) 715–723 (ACM, 2018).

    Not in our library

36. 36.

    Rahhal MA, et al. Deep learning approach for active classification of electrocardiogram signals. Inf. Sci. 2016;345:340-354.

    Not in our library10.1016/j.ins.2016.01.082

37. 37.

    Goldberger AL, et al. PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation. 2000;101:E215-E220.

    Not in our library10.1161/01.cir.101.23.e215

38. 38.

    Goto S, et al. Artificial intelligence to predict needs for urgent revascularization from 12-leads electrocardiography in emergency patients. PLoS ONE. 2019;14:e0210103.

    Not in our library10.1371/journal.pone.0210103

39. 39.

    Rautaharju PM, Surawicz B, Gettes LS. AHA/ACCF/HRS Recommendations for the Standardization and Interpretation of the Electrocardiogram: Part IV: The ST Segment, T and U Waves, and the QT Interval 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. 2009;53:982-991.

    Not in our library10.1016/j.jacc.2008.12.014

40. 40.

    Luo S, Johnston P. A review of electrocardiogram filtering. J. Electrocardiol. 2010;43:486-496.

    Not in our library10.1016/j.jelectrocard.2010.07.007

41. 41.

    Nascimento BR, Brant LCC, Marino BCA, Passaglia LG, Ribeiro ALP. Implementing myocardial infarction systems of care in low/middle-income countries. Heart. 2019;105:20.

    Not in our library10.1136/heartjnl-2018-313398

42. 42.

    Macfarlane P, et al. Methodology of ECG interpretation in the Glasgow program. Methods Inf. Med. 1990;29:354-361.

    Not in our library10.1055/s-0038-1634799

43. 43.

    Macfarlane PW, Latif S. Automated serial ECG comparison based on the Minnesota code. J. Electrocardiol. 1996;29:29-34.

    Not in our library10.1016/s0022-0736(96)80016-1

44. 44.

    Prineas, R. J., Crow, S. & Zhang, Z. M. The Minnesota Code Manual of Electrocardiographic Findings (Springer Science & Business Media, 2009).

    Not in our library

45. 45.

    Veloso, A., Meira, W. Jr. & Zaki, M. J. Lazy associative classification. In Proc. 6th International Conference on Data Mining (ICDM) 645–654 (IEEE Computer Society, 2006).

    Not in our library

46. 46.

    Cohen J. A coefficient of agreement for nominal scales. Educ. Psychological Meas. 1960;20:37-46.

    Not in our library10.1177/001316446002000104

47. 47.

    Kligfield P, et al. Recommendations for the standardization and interpretation of the electrocardiogram. J. Am. Coll. Cardiol. 2007;49:1109.

    Not in our library10.1016/j.jacc.2007.01.024

48. 48.

    He, K., Zhang, X., Ren, S. & Sun, J. Identity mappings in deep residual networks. In Computer Vision—ECCV 2016 (eds Leibe, B. et al.) 630–645 (Springer International Publishing, 2016).

    Not in our library

49. 49.

    Ioffe, S. & Szegedy, C. Batch normalization: accelerating deep network training by reducing internal covariate shift. In Proc. 32nd International Conference on Machine Learning (eds Bach, F. & Blei, D.) 448–456 (JMLR.org, PMLR, 2015).

    Not in our library

50. 50.

    Srivastava N, Hinton GE, Krizhevsky A, Sutskever I, Salakhutdinov R. Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 2014;15:1929-1958.

    Not in our library

51. 51.

    Hutchison, D. et al. Evaluation of pooling operations in convolutional architectures for object recognition. In Artificial Neural Networks—ICANN 2010 Vol. 6354 (eds Diamantaras, K. et al.) 92–101 (Springer, Berlin, 2010).

    Not in our library

52. 52.

    Kingma, D. P. & Ba, J. Adam: a method for stochastic optimization. In Proc. 3rd International Conference for Learning Representations (ICLR) (eds Bengio, Y. & LeCun, Y.) (Conference Track Proceedings, San Diego, CA, USA, 2015). http://arxiv.org/abs/1412.6980.

    Not in our library

53. 53.

    He, K., Zhang, X., Ren, S. & Sun, J. Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In Proc. IEEE International Conference on Computer Vision 1026–1034 (2015).

    Not in our library

54. 54.
    The Precision-Recall Plot Is More Informative than the ROC Plot When Evaluating Binary Classifiers on Imbalanced Datasets · 2015

    No notice

Cited by papers we hold 4

• Linking Electrocardiogram and Echocardiogram: Comparing Classical Machine Learning and Deep Learning Neural Networks for the Detection of Regional Wall Motion Abnormalities · 2025
  Not checked
• Multimodal Deep Learning for Prognosis Prediction in Renal Cancer · 2021
  Not checked
• Critical appraisal of a machine learning paper: A guide for the neurologist · 2021
  Not checked
• Deep neural network-estimated electrocardiographic age as a mortality predictor · 2021
  No notice

Reads

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.