Existing users Log In New users Sign up


Machine Learning in ECG Interpretation

DISCOVERIES (ISSN 2359-7232), 2017, July-September issue

CITATION: 

Ponomariov V, Chirila L, Apipie FM, Abate R, Rusu M, Wu Z, Liehn EA, Bucur I. Artificial Intelligence versus Doctors’ Intelligence: A Glance on Machine Learning Benefaction in Electrocardiography, Discoveries 2017, Jul-Oct; 5(3): e76. DOI: 10.15190/d.2017.6

Submitted: May 20th, 2017; Revised: Sept. 28th, 2017; Accepted: Sept. 29th, 2017; Published: Sept. 30th, 2017;

 GO BACK to 2017, July-September issue

 GO BACK to DISCOVERIES

Artificial Intelligence versus Doctors’ Intelligence: A Glance on Machine Learning Benefaction in Electrocardiography

Victor Ponomariov (1,2), Liviu Chirila (3), Florentina-Mihaela Apipie (4,5), Raffaele Abate (3,6), Mihaela Rusu (1), Zhuojun Wu (1,4), Elisa A. Liehn (1,2,7), Ilie Bucur (4, *)

(1) Institute for Molecular Cardiovascular Research (IMCAR), RWTH Aachen University, Germany;

(2) Department of Cardiology, Pulmonology, Angiology and Intensive Care, University Hospital, RWTH Aachen University, Germany;

(3) ECUORE LTD, London, England;

(4) Applied Systems srl, Craiova, Romania;

(5) Faculty of Economic and Business Administration, Doctoral School of Economics, University of Craiova, Romania;

(6) School of Medicine, University of Catania, Italy;

(7) Human Genetic Laboratory, University of Medicine and Pharmacy, Craiova, Romania;


*Corresponding author: Ilie Bucur, PhD, Applied Systems srl, Craiova, Romania; Email: bucur_il@yahoo.com 

Abstract

Computational machine learning, especially self-enhancing algorithms, prove remarkable effectiveness in applications, including cardiovascular medicine. This review summarizes and cross-compares the current machine learning algorithms applied to electrocardiogram interpretation. In practice, continuous real-time monitoring of electrocardiograms is still difficult to realize. Furthermore, automated ECG interpretation by implementing specific artificial intelligence algorithms is even more challenging. By collecting large datasets from one individual, computational approaches can assure an efficient personalized treatment strategy, such as a correct prediction on patient-specific disease progression, therapeutic success rate and limitations of certain interventions, thus reducing the hospitalization costs and physicians’ workload. Clearly such aims can be achieved by a perfect symbiosis of a multidisciplinary team involving clinicians, researchers and computer scientists. Summarizing, continuous cross-examination between machine intelligence and human intelligence is a combination of precision, rationale and high-throughput scientific engine integrated into a challenging framework of big data science.

Access full text of the manuscript here: 

References

1. Itchhaporia D, Snow PB, Almassy RJ, Oetgen WJ. Artificial neural networks: Current status in cardiovascular medicine. J Am Coll Cardiol 1996;28:515-521.

2. Kshirsagar PR, Akijwar SG, Dhanoriya R. Classification of ECG-signals using Artificial Neural Networks. 2017; Conference Paper.

3. Kononenko I. Machine learning for medical diagnosis: history, state of the art and perspective. Artif Intell Med 2001;23:89-109.

4. Ramesh AN, Kambhampati C, Monson JRT, Drew PJ. Artificial intelligence in medicine. Ann Royal Coll Surg Engl 2004;86:334-338.

5. Sun Y, Cheng AC. Machine learning on-a-chip: a high-performance low-power reusable neuron architecture for artificial neural networks in ECG classifications. Comp Biol Med 2012;42:751-7.

6. Papaloukas C, Fotiadis DI, Likas A, Michalis LK. An ischemia detection method based on artificial neural networks. Artif Intell Med 2002;24:167-178.

7. Haghpanahi M, Borkholder DA. Fetal QRS extraction from abdominal recordings via model-based signal processing and intelligent signal merging. Physiol Measurement 2014;35:1591-605.

8. Houshyarifar V, Chehel Amirani M. An approach to predict Sudden Cardiac Death (SCD) using time domain and bispectrum features from HRV signal. Bio-Med Mat Eng 2016;27:275-85.

9. Papadimitriou S, Mavroudi S, Vladutu L, Bezerianos A. Ischemia detection with a self-organizing map supplemented by supervised learning. IEEE transactions on neural networks 2001;12:503-15.

10. Hudson DL, Cohen ME. Neural networks and artificial intelligence for biomedical engineering: Wiley Online Library, 2000.

11. Zacharia AM, Shyjila PA, Kizhakkethottam JJ. Cardiac Arrhythmia Classification Using Atrial Activity Signal. Procedia Technology 2016;24:1406-1414.

12. Samuel AL. Some Studies in Machine Learning Using the Game of Checkers IBM. J Res Develop 1959;3:211-229.

13. Kononenko I. Machine learning for medical diagnosis: history, state of the art and perspective. Artif Intell Med 2001;23:89-109.

14. Vayena E, Salathe M, Madoff LC, Brownstein JS. Ethical challenges of big data in public health. PLoS Comput Biol 2015;11:e1003904.

15. Salathe M. Digital Pharmacovigilance and Disease Surveillance: Combining Traditional and Big-Data Systems for Better Public Health. J Infect Dis 2016;214:S399-S403.

16. Salathe M, Khandelwal S. Assessing vaccination sentiments with online social media: implications for infectious disease dynamics and control. PLoS Comput Biol 2011;7:e1002199.

17. White RW, Tatonetti NP, Shah NH, Altman RB, Horvitz E. Web-scale pharmacovigilance: listening to signals from the crowd. J Am Med Inform Assoc 2013;20:404-8.

18. Velasco E, Agheneza T, Denecke K, Kirchner G, Eckmanns T. Social media and internet-based data in global systems for public health surveillance: a systematic review. Milbank Q 2014;92:7-33.

19. Rodier G, Greenspan AL, Hughes JM, Heymann DL. Global public health security. Emerg Infect Dis 2007;13:1447-52.

20. Krittanawong C, Zhang H, Wang Z, Aydar M, Kitai T. Artificial Intelligence in Precision Cardiovascular Medicine. J Am Coll Cardiol 2017;69:2657-2664.

21. Wolf MJ, Lee EK, Nicolson SC et al. Rationale and methodology of a collaborative learning project in congenital cardiac care. Am Heart J 2016;174:129-37.

22. Sansone M, Fusco R, Pepino A, Sansone C. Electrocardiogram pattern recognition and analysis based on artificial neural networks and support vector machines: a review. J Healthc Eng 2013;4:465-504.

23. Gao D, Madden M, Chambers D, Lyons G. Bayesian ANN classifier for ECG arrhythmia diagnostic system: A comparison study. Neural Networks, 2005 IJCNN'05 Proceedings 2005 IEEE International Joint Conference on: IEEE, 2005:2383-2388.

24. Gothwal H, Kedawat S, Kumar R. Cardiac arrhythmias detection in an ECG beat signal using fast fourier transform and artificial neural network. J Biomed Sci Eng 2011;04:289-296.

25. Poorahangaryan F, Kiani A, Karami A, Zanj B. ECG arrhythmias detection using a new intelligent system based on neural networks and Wavelet transform, J Electrocardiol, 2012; 39(4): S152-6. 

26. Birnie DH, Sauer WH, Bogun F et al. HRS Expert Consensus Statement on the Diagnosis and Management of Arrhythmias Associated With Cardiac Sarcoidosis. Heart Rhythm 2014;11:1304-1323.

27. de Albuquerque VHC, Nunes TM, Pereira DR et al. Robust automated cardiac arrhythmia detection in ECG beat signals. Neural Computing and Applications 2016.

28. Luz EJdS, Schwartz WR, Cámara-Chávez G, Menotti D. ECG-based heartbeat classification for arrhythmia detection: A survey. Comp Meth Prog Biomed 2016;127:144-164.

29. Goodfellow I. BY, Courville A. Deep Learning: MIT Press, 2016.

30. Lecun Y. BB, Denker J.S., Henderson D., Howard R.E., Hubbard W., Jackel L.D. Backpropagation applied to handwritten zipcode recognition. Neutral Computation 1989;1:541-551.

31. Ciresan D.C. MU, Gambardella L. M., Schmidhuber J. Convolutional Neural Network Committees for Handwritten Character Classification. Proceedings of the 2011 International Conference on Document Analysis and Recognition: IEEE Computer Society Washington, 2011:1135-1139.

32. Zimmerman-Moreno G, Marin I, Lindner M et al. Automatic classification of cancer cells in multispectral microscopic images of lymph node samples. Conference proceedings : Ann Internat Conf IEEE Eng Med Biol Soc 2016;2016:3973-3976.

33. Guvenir HA, Acar B, Demiroz G, Cekin A. A supervised machine learning algorithm for arrhythmia analysis. 1997:433-436.

34. Gutiérrez-Gnecchi JA, Morfin-Magaña R, Lorias-Espinoza D et al. DSP-based arrhythmia classification using wavelet transform and probabilistic neural network. Biomed Sign Proc Cont 2017;32:44-56.

35. Sahoo S, Biswal P, Das T, Sabut S. De-noising of ECG Signal and QRS Detection Using Hilbert Transform and Adaptive Thresholding. Procedia Technology 2016;25:68-75.

36. Varanini M, Tartarisco G, Billeci L, Macerata A, Pioggia G, Balocchi R. An efficient unsupervised fetal QRS complex detection from abdominal maternal ECG. Physiol measurement 2014;35:1607-19.

37. Rodriguez-Sotelo J.L. C-FD, Castellanos-Domingeuz G. An Improved Method for Unsupervised Analysis of ECG Beats Based on WT Features and J-Means Clustering. Computers in Cardiol 2007;34:581-584.

38. Muth S, Dort S, Sebag IA, Blais MJ, Garcia D. Unsupervised dealiasing and denoising of color-Doppler data. Medical image analysis 2011;15:577-88.

39. Miotto R, Li L, Kidd BA, Dudley JT. Deep Patient: An Unsupervised Representation to Predict the Future of Patients from the Electronic Health Records. Scientific reports 2016;6:26094.

40. Haldar NAH, Khan FA, Ali A, Abbas H. Arrhythmia classification using Mahalanobis distance based improved Fuzzy C-Means clustering for mobile health monitoring systems. Neurocomputing 2017;220:221-235.

41. Witten I.H. FE, Hall M.A. Data Mining: Practical Machine Learning Tools and Techniques (Third Edition) 2011.

42. Kiranyaz S, Ince T, Gabbouj M. Real-Time Patient-Specific ECG Classification by 1-D Convolutional Neural Networks. IEEE transactions on bio-medical engineering 2016;63:664-75.

43. Badilini F, Sarapa N. Implications of methodological differences in digital electrocardiogram interval measurement. J Electrocardiol 2006;39:S152-6.

44. Vijayavanan M, Rahtikarani V, Dhanalakshmi P. Automatic Classification of ECG Signal for Heart Disease Diagnosis using morphological features. Internat J Conp Sci Eng Tech 2014;5:449-455.

45. Tang X, Shu L. Classification of Electrocardiogram Signals with RS and Quantum Neural Network. Internat J Multimedia Ubiquitous Eng 2014;9:363-372.

46. Weng S, Reps J, Kai J, Garibaldi J, Qureshi N. Can machine-learning improve cardiovascular risk prediction using routine clinical data? PLoS ONE 2017;12.

47. Brunetti ND, De Gennaro L, Correale M et al. Pre-hospital electrocardiogram triage with telemedicine near halves time to treatment in STEMI: A meta-analysis and meta-regression analysis of non-randomized studies. Internat J Cardiol 2017;232:5-11.

48. Hosseini HG, Luo D, Reynolds KJ. The comparison of different feed forward neural network architectures for ECG signal diagnosis. Medical Engineering & Physics 2006;28:372-378.

49. Jatmiko W, Nulad W, Elly M, Setiawan IMA, Mursanto P. Heart beat classification using wavelet feature based on neural network. WSEAS Transactions on Systems 2011;10:17-26.

50. Kara S, Okandan M. Atrial fibrillation classification with artificial neural networks. Pattern Recognition 2007;40:2967-2973.

51. Kim J, Shin H, Shin K, Lee M. Robust algorithm for arrhythmia classification in ECG using extreme learning machine. BioMedical Engineering OnLine 2009;8:31.

52. Melgan F, Bazi Y. Classification of electrocardiogram signals with support vector machines and particle swarm optimization. IEEE Trans Inform Tech Biomed 2008;12:667-677.

53. Mitra M, Samanta RK. Cardiac Arrhythmia Classification Using Neural Networks with Selected Features. Procedia Technology 2013;10:76-84.

54. Mohamed B, Issam A, Mohamed A, Abdellatif B. ECG Image Classification in Real time based on the Haar-like Features and Artificial Neural Networks. Procedia Computer Science 2015;73:32-39.

55. Özdemir AT, Danișman K. Fully parallel ANN-based arrhythmia classifier on a single-chip FPGA: FPAAC. Turkish J Electrical Eng Comp Sci 2011;19:667-687.

56. Rajendra Acharya U, Subbanna Bhat P, Iyengar SS, Rao A, Dua S. Classification of heart rate data using artificial neural network and fuzzy equivalence relation. Pattern Recognition 2003;36:61-68.

57. Remya RS, Indiradevi KP, Babu KKA. Classification of Myocardial Infarction Using Multi Resolution Wavelet Analysis of ECG. Procedia Technology 2016;24:949-956.

58. Saini R. Classification of arrhythmia based on vebf neural network. International J Eng Res Appl (IJERA) 2012;2:1863-1866.

59. Srinivas N, Babu AV, M.D.Rajak. ECG Signal Analysis Using Data Clustering and Artificial Neural Network. Am Internat J Res Sci Tech Eng Math 2013;13.

60. Song MH, Lee J, Cho SP, Lee KJ, Yoo SK. Support Vector Machine Based Arrhythmia Classification Using Reduced Features. Internat J Cont Autom Syst 2005;3:571-579.

61. Asl BM, Setarehdan SK, Mohebbi M. Support vector machine-based arrhythmia classification using reduced features of heart rate variability signal. Artif Intell Med 2008;44:51-64.

62. Lima CAM, Coelho ALV, Eisencraft M. Tackling EEG signal classification with least squares support vector machines: A sensitivity analysis study. Comp Biol Med 2010;40:705-714.

63. Zidelmal Z, Amirou A, Ould-Abdeslam D, Merckle J. ECG beat classification using a cost sensitive classifier. Computer Meth Prog Biomed 2013;111:570-577.

64. Das MK, Ari S. Patient-specific ECG beat classification technique. Health Techn Lett 2014;1:98-103.

65. Li T, Zhou M. ECG Classification Using Wavelet Packet Entropy and Random Forests. Entropy 2016;18:285.

66. Faziludeen S, Sankaran P. ECG Beat Classification Using Evidential K -Nearest Neighbours. Procedia Comp Sci 2016;89:499-505.

67. Kutlu Y, Kuntalp D. Feature extraction for ECG heartbeats using higher order statistics of WPD coefficients. Computer Meth Prog Biomed 2012;105:257-267.

News & Events Latest news from Discoveries

  • 2018 | For Authors!

    PMC highlighted that a high proportion of authors of Discoveries articles are also members of our Editorial Board. As a result, from now on and for at least 1 year, we will only accept articles from authors that are NOT members of Discoveries' Editorial Board. All articles submitted by our members will be immediately rejected until further notice (one accepted article was already rejected). 

  • 2017-2018 | PubMed inclusion News!

    Discoveries successfully passed the Scientific Quality Review by NLM-NIH for PubMedCentral and PubMed indexing. This is the first and the most important step towards PubMedCentral and PubMed indexing! The second (last) step is the Technical Review.

  • April 2016 | Faster Peer-Review

    Starting on April 13th 2016, all articles selected for a peer-review will receive the post peer-review decision within 10 days. The initial pre-screening time will remain the same (48h from the submission of the manuscript). This decision will significantly accelerate the publication, with no effect on the quality of the peer-review process.

  • February 2016 | Manuscript submission

    Discoveries is commited to excellence, quality and high editorial standards. We are receiving an increasing number of manuscripts for which the identity of the authors/corresponding author can't be verified. Please NOTE that ALL these articles were and will be immediately REJECTED. Indicating an institutional email address is the easiest way to overcome this problem! Moreover, we do not accept any pressure on our editorial board to accept a manuscript. This results in a prompt rejection of the article.

    Editorial Policies
  • January 2016 | Main Objective

    After reaching all proposed milestones until now (including being indexed by Google Scholar in 2014), Discoveries' next Aim is PubMed indexing of all its articles (already published and upcoming). There will be no charge for the submission or publication of articles before Discoveries is indexed.

  • August 2015 | Discoveries - on PubMed

    We are happy to announce that our first Discoveries articles were included in PMC and PubMed. More articles (submitted by NIH funded authors) are now processed for being included.

    Discoveries articles now on PubMed
  • April 2015 | Special Issue

    DISCOVERIES published the SPECIAL ISSUE entitled "INFLAMMATION BETWEEN DEFENSE AND DISEASE: Impact on Tissue Repair and Chronic Sickness".

    Special Issue on "Inflammation"
  • 2015 | Ischemia Collection

    DISCOVERIES launched a call for papers for a Collection of Articles with focus on "ISCHEMIA". If you are interested to submit a manuscript, please contact us at info@discoveriesjournals.org

  • September 2014 | Special Issue

    DISCOVERIES just publish the SPECIAL ISSUE entitled "CELL SECRETION & MEMBRANE FUSION" in September 2014. Initially scheduled for publication between October 2014-March 2015, this issue was successfully published earlier than scheduled. 

    Special Issue
  • April 2014 | Indexed by Google Scholar

    All our published articles are now indexed by Google Scholar! First citations to Discoveries articles are included! Search for the article's title (recommended) or the authors:

    Google Scholar Search
  • 2014 | DISCOVERIES

    DOIs (Digital Object Identifiers) are now assigned to all our published manuscripts in Discoveries. DOI uniquely identifies an article and is provided by CrossRef.

    CrossRef
  • July 2013 | Manuscript Submission

    Submit your manuscript FREE, FAST and EASY ! (in less than 1 minute)! There are NO fees for the manuscript submission or publishing of the accepted manuscripts.
    read more

  • July 2013 | DISCOVERIES

    We are now ACCEPTING MANUSCRIPTS for publishing in DISCOVERIES. We aim publishing a small number of high impact experimental articles & reviews (around 40/year) to maintain a high impact factor. Domains of interest: all areas related to Medicine, Biology and Chemistry ...

    read more
Member Login
Free Registration Click here to sign up
Copyright © 2013 Applied Systems. All Rights Reserved.