Soft Computing

, Volume 23, Issue 12, pp 4207–4219 | Cite as

Automatic identification of characteristic points related to pathologies in electrocardiograms to design expert systems

  • Jose Ignacio Peláez
  • Jose Antonio Gomez-RuizEmail author
  • Javier Fornari
  • Gustavo F. Vaccaro
Methodologies and Application


Electrocardiograms (ECG) record the electrical activity of the heart through 12 main signals called shunts. Medical experts examine certain segments of these signals in where they believe the cardiovascular disease is manifested. This fact is an important determining factor for designing expert systems for cardiac diagnosis, as it requires the direct expert opinion in order to locate these specific segments in the ECG. The main contributions of this paper are: (i) to propose a model that uses the full ECG signal to identify key characteristic points that define cardiac pathology without medical expert intervention and (ii) to present an expert system based on artificial neural networks capable of detecting bundle branch block disease using the previous approach. Cardiologists have validated the proposed model application and a comparative analysis is performed using the MIT-BIH arrhythmia database.


ECG Cardiovascular disease Bundle branch blocks Medical diagnosis Multilayer perceptron 



We thank the Regional University Hospital of Malaga, Unit of Heart Clinic and Vascular Pathology, their collaboration in the review and validation of the results obtained by the proposed model. This work is part of a project funded by the Ministry of Industry, Tourism and Commerce (TSI-020302-2010-136) and University of Malaga (81434547001-3). The authors are grateful to anonymous reviewers for their valuable comments.

Compliance with ethical standards

Conflict of interest

All authors declare that they have no conflict of interest.


  1. Abbasi R, Esmaeilpour M (2017) Selecting statistical characteristics of brain signals to detect epileptic seizures using discrete wavelet transform and perceptron neural network. Int J Interact Multimed Artif Intell 4(5):33–38. Google Scholar
  2. Akay M, Semmlow JL, Welkowitz W, Bauer MD (1990) Noninvasive detection of coronary stenoses before and after angioplasty using eigenvector methods. IEEE Trans Biomed Eng 37(11):1095–1104Google Scholar
  3. Bayés de Luna A (2006) Semiología electrocardiográfica II: Patrones diagnósticos de crecimiento, bloqueos y preexcitación. Prous Science, BarcelonaGoogle Scholar
  4. Benali R, Bereksi Reguig F, Hadj Slimane Z (2012) Automatic classification of heartbeats using wavelet neural networks. J Med Syst 36(2):883–892Google Scholar
  5. Ceylan R, Özbay Y (2007) Comparison of FCM, PCA and WT techniques for classification ECG arrhythmias using artificial neural network. Expert Syst Appl 33(2):286–295. Google Scholar
  6. Chang PC, Wu JL, Xu Y, Zhang M, Lu XI (2017) Bike sharing demand prediction using artificial immune system and artificial neural network. Soft Comput. Google Scholar
  7. Chazal F, Reilly RB (2006) A patient adapting heart beat classifier using ECG morphology and heartbeat interval features. IEEE Trans Biomed Eng 53(12):2535–2543Google Scholar
  8. Chazal P, O’Dwyer M, Reilly RB (2004) Automatic classification of heartbeats using ECG morphology and heartbeat interval features. IEEE Trans Bio-Med Eng 51(7):1196–1206. Google Scholar
  9. Daubechies I (1994) Ten lectures on wavelets. Capital City Press, VermontzbMATHGoogle Scholar
  10. De Jesús Rubio J (2017) A method with neural networks for the classification of fruits and vegetables. Soft Comput 21:7207–7220. Google Scholar
  11. Dokur Z, Ölmez T (2001) ECG beat classification by a novel hybrid neural network. Comput Methods Progr Biomed 66(2–3):167–181. Google Scholar
  12. Dokur Z, Olmez T, Yazgan E (1999) Comparison of discrete wavelet and Fourier transforms for ECG beat classification. Electron Lett 35(18):1502–1504. Google Scholar
  13. Esmaeilpour M, Mohammadi ARA (2016) Analyzing the EEG signals in order to estimate the depth of anesthesia using wavelet and fuzzy neural networks. Int J Interact Multimed Artif Intell 4(2):12–15. Google Scholar
  14. Figuereido Dalvi R, Tozatto Zago G, Varejão Andreão R (2016) Heartbeat classification system based on neural networks and dimensionality reduction. Res Biomed Eng 32(4):318–326. Google Scholar
  15. Gacek A, Pedrycz W (2013) Description, analysis, and classification of biomedical signals: a computational intelligence approach. Soft Comput 17(9):1659–1671. Google Scholar
  16. Ge D, Srinivasan N, Krishnan SM (2002) Cardiac arrhythmia classification using autoregressive modeling. Biomed Eng Online 1(1):5. Google Scholar
  17. Gholam Hosseini H, Luo D, Reynolds KJ (2006) The comparison of different feed forward neural network architectures for ECG signal diagnosis. Med Eng Phys 28(4):372–378. Google Scholar
  18. GholamHosseini H, Nazeran H, Moran B (1998) ECG compression: evaluation of FFT, DCT, and WT performance. Australas Phys Eng Sci Med 21(4):186–192Google Scholar
  19. Goldberger AL, Amaral LAN, Glass L, Hausdorff JM, Ivanov PC, Mark RG, Mietus JE, Moody GB, Peng C-K, Stanley HE (2000) PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals. Circulation 101(23):215–220. Google Scholar
  20. Güler I, Übeyli ED (2005) ECG beat classifier designed by combined neural network model. Pattern Recogn 38(2):199–208. Google Scholar
  21. Hadj Slimane ZE, Bereksi Reguig F (2005) New algorithm for QRS complex detection. J Mech Med Biol 5(4):507. Google Scholar
  22. Haykin S (2008) Neural networks and learning machines, 3er edn. Pearson, LondonGoogle Scholar
  23. He L, Hou W, Zhen X, Peng C (2006) Recognition of ECG patterns using artificial neural network. In: Sixth international conference on intelligent systems design and applications, pp 477–481. EEE, Jinan.
  24. Hosseini HG, Luo D, Reynolds KJ (2006) The comparison of different feed forward neural network architectures for ECG signal diagnosis. Med Eng Phys 28(4):372–378. Google Scholar
  25. Hyvärinen A (1999) Fast and robust fixed-point algorithms for independent component analysis. IEEE Trans Neural Netw 10(3):626–634Google Scholar
  26. Hyvärinen A, Oja E (1997) A fast fixed-point algorithm for independent component analysis. Neural Comput 9:1483–1492Google Scholar
  27. Hyvärinen A, Karhunen J, Oja E (2001) Independent component analysis. Wiley, FinlandGoogle Scholar
  28. Ikeda M, Oda T, Barolli L (2017) A vegetable category recognition system: a comparison study for caffe and Chainer DNN frameworks. Soft Comput. Google Scholar
  29. Jekova I, Bortolan G, Christov I (2008) Assessment and comparison of different methods for heartbeat classification. Med Eng Phys 30(2):248–257. Google Scholar
  30. Kang S (2017) Outgoing call recommendation using neural network. Soft Comput. Google Scholar
  31. Karanik M, Wanderer L, Gomez-Ruiz JA, Pelaez JI (2016) Reconstruction methods for AHP pairwise matrices: How reliable are they? Appl Math Comput 279:103–124. MathSciNetzbMATHGoogle Scholar
  32. Khorrami H, Moavenian M (2010) A comparative study of DWT, CWT and DCT transformations in ECG arrhythmias classification. Expert Syst Appl 37(8):5751–5757. Google Scholar
  33. Korürek M, Dogan B (2010) ECG beat classification using particle swarm optimization and radial basis function neural network. Expert Syst Appl 37(12):7563–7569. Google Scholar
  34. Kumar SU, Inbarani HH (2017) Neighborhood rough set based ECG signal classification for diagnosis of cardiac diseases. Soft Comput 21:4721–4733. Google Scholar
  35. Lagerholm M, Peterson C, Braccini G, Edenbrandt L, Sornmo L (2000) Clustering ECG complexes using Hermite functions and self-organizing maps. IEEE Trans Biomed Eng 47(7):838–847. Google Scholar
  36. Li H, Yuan D, Ma X, Cui D, Cao L (2017) Genetic algorithm for the optimization of features and neural networks in ECG signals classification. Nat Sci Rep 7:41011. Google Scholar
  37. Linh TH, Osowsky S (2003) On-line heart beat recognition using hermite polynomials and neuro-fuzzy network. IEEE Trans Instrum Meas 52(4):1224–1231Google Scholar
  38. Ljung L (1999) System identification: theory for the user. Prentice Hall, Englewood CliffszbMATHGoogle Scholar
  39. Mallet S (1999) A wavelet tour of signal processing. Academic Press, San DiegoGoogle Scholar
  40. Marple SL (1987) Digital spectral analysis with applications. Prentice Hall, Englewood CliffsGoogle Scholar
  41. Martis RJ, Krishnan MM, Chakraborty C, Pal S, Sarkar D, Mandana KM, Ray AK (2012) Automated screening of arrhythmia using wavelet based machine learning techniques. J Med Syst 36(2):677–688. Google Scholar
  42. Melgani F, Bazi Y (2008) Classification of electrocardiogram signals with support vector machines and particle swarm optimization. IEEE Trans Inf Technol Biomed 12(5):667–677. Google Scholar
  43. Moon H-M, Seo CH, Pan SB (2017) A face recognition system based on convolution neural network using multiple distance face. Soft Comput 21(17):4995–5002. Google Scholar
  44. Ocak H (2009) Automatic detection of epileptic seizures in EEG using discrete wavelet transform and approximate entropy. Expert Syst Appl 36(2):2027–2036Google Scholar
  45. Osowski S, Stodolski M (2003) On-line heart beat recognition using hermite polynomials and neuro-fuzzy network. IEEE Trans Instrum Meas 52(4):1224–1231. Google Scholar
  46. Pahlm O, Sörnmo L (1984) Software QRS detection in ambulatory monitoring—a review. Med Biol Eng Comput 22(4):289–297. Google Scholar
  47. Pan J, Tompkins WJ (2007) A real-time QRS detection algorithm. IEEE Trans Biomed Eng 32(3):230–236. Google Scholar
  48. Park J, Kang M, Gao J, Kim Y, Kang K (2017) Cascade classification with adaptive feature extraction for arrhythmia detection. J Med Syst 41:11. Google Scholar
  49. Patel OP, Tiwari A, Chaudhary R, Nuthalapati SV, Bharill N, Prasad M, Hussain FK, Hussain OK (2017) Enhanced quantum-based neural network learning and its application to signature verification. Soft Comput. Google Scholar
  50. Percy SF, Piedrahita AM, Escobar RF, Gonzalez Crespo R (2017) Comparison of neural network topologies for the classification of frogs by their songs. Soft Comput 21:7099–7106. Google Scholar
  51. Pławiak P (2018) Novel methodology of cardiac health recognition based on ECG signals and evolutionary-neural system. Expert Syst Appl 92:334–349. Google Scholar
  52. Plaza-Leiva V, Gomez-Ruiz JA, Mandow A, García-Cerezo A (2017) Voxel-based neighborhood for spatial shape pattern classification of lidar point clouds with supervised learning. Sensors 17(3):594. Google Scholar
  53. Rathore SS, Kumar S (2017) An empirical study of some software fault prediction techniques for the number of faults prediction. Soft Comput 21(24):7417–7434. Google Scholar
  54. Sadrawi M, Lin C-H, Lin Y-T, Hsieh Y, Kuo C-C, Chien JC, Haraikawa K, Abbod MF, Shieh J-S (2017) Arrhythmia evaluation in wearable ECG devices. Sensors 17(11):2445. Google Scholar
  55. Sharma P, Chandra Ray K (2016) Efficient methodology for electrocardiogram beat classification. IET Signal Process 10(7):825–832. Google Scholar
  56. Singh BN, Tiwari AK (2006) Optimal selection of wavelet basis function applied to ECG signal denoising. Digit Signal Proc 16(3):275–287. Google Scholar
  57. So HH, Chan KL (1997) Development of QRS detection method for real-time ambulatory cardiac monitor. In: Proceedings of the 19th annual international conference of the IEEE engineering in medicine and biology society. IEEE, Chicago, IL, pp 289–292.
  58. Strang G, Nguyen T (1996) Wavelets and filter banks. Cambridge Press, WillesleyzbMATHGoogle Scholar
  59. Thakor NV, Webster JG, Tompkins WJ (1983) Optimal QRS detector. Med Biol Eng Comput 21(3):343–350. Google Scholar
  60. Übeyli ED (2009) Combining recurrent neural networks with eigenvector methods for classification of ECG beats. Digit Signal Proc 19(2):320–329. Google Scholar
  61. Übeyli ED, Güler I (2003) Comparison of eigenvector methods with classical and model-based methods in analysis of internal carotid arterial Doppler signals. Comput Biol Med 33(6):473–493Google Scholar
  62. Wang X, Paliwal KK (2003) Feature extraction and dimensionality reduction algorithms and their applications in vowel recognition. Pattern Recogn 36(10):2429–2439. zbMATHGoogle Scholar
  63. Wei J-J, Chang C-J, Chou N-K, Jan G-J (2002) ECG data compression using truncated singular value decomposition. IEEE Trans Inf Technol Biomed 5(4):290–299. Google Scholar
  64. Xia Y, Wulan N, Wang K, Zhang H (2018) Detecting atrial fibrillation by deep convolutional neural networks. Comput Biol Med 93:84–92. Google Scholar
  65. Yu SN, Chou KT (2009) Selection of significant independent components for ECG beat classification. Expert Syst Appl 36(2):2088–2096. Google Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Department of Languages and Computer SciencesUniversity of MalagaMálagaSpain
  2. 2.Institute of Biomedical Research of Malaga (IBIMA)MálagaSpain
  3. 3.National Technological UniversityRafaelaArgentina
  4. 4.Secretariat of Higher Education, Innovation, Science, and Technology (SENESCYT)GuayaquilEcuador

Personalised recommendations