Medical Decision Support System for Diagnosis of Heart Arrhythmia using DWT and Random Forests Classifier

  • Emina Alickovic
  • Abdulhamit SubasiEmail author
Patient Facing Systems
Part of the following topical collections:
  1. Patient Facing Systems


In this study, Random Forests (RF) classifier is proposed for ECG heartbeat signal classification in diagnosis of heart arrhythmia. Discrete wavelet transform (DWT) is used to decompose ECG signals into different successive frequency bands. A set of different statistical features were extracted from the obtained frequency bands to denote the distribution of wavelet coefficients. This study shows that RF classifier achieves superior performances compared to other decision tree methods using 10-fold cross-validation for the ECG datasets and the obtained results suggest that further significant improvements in terms of classification accuracy can be accomplished by the proposed classification system. Accurate ECG signal classification is the major requirement for detection of all arrhythmia types. Performances of the proposed system have been evaluated on two different databases, namely MIT-BIH database and St. -Petersburg Institute of Cardiological Technics 12-lead Arrhythmia Database. For MIT-BIH database, RF classifier yielded an overall accuracy 99.33 % against 98.44 and 98.67 % for the C4.5 and CART classifiers, respectively. For St. -Petersburg Institute of Cardiological Technics 12-lead Arrhythmia Database, RF classifier yielded an overall accuracy 99.95 % against 99.80 % for both C4.5 and CART classifiers, respectively. The combined model with multiscale principal component analysis (MSPCA) de-noising, discrete wavelet transform (DWT) and RF classifier also achieves better performance with the area under the receiver operating characteristic (ROC) curve (AUC) and F-measure equal to 0.999 and 0.993 for MIT-BIH database and 1 and 0.999 for and St. -Petersburg Institute of Cardiological Technics 12-lead Arrhythmia Database, respectively. Obtained results demonstrate that the proposed system has capacity for reliable classification of ECG signals, and to assist the clinicians for making an accurate diagnosis of cardiovascular disorders (CVDs).


Electrocardiogram (ECG) Multiscale Principal Component Analysis (MSPCA) Discrete Wavelet Transform (DWT) Decision Tree Random Forest (RF) Heart arrhythmia 


Compliance with Ethical Standards

Conflict of Interest

The authors declare that they have no conflict of interest.


  1. 1.
    Acharya, U. R., Automatic identification of cardiac health using modeling techniques: a comparative study. Inf. Sci. 178:4571–4582, 2008.CrossRefGoogle Scholar
  2. 2.
    Acır, N., A support vector machine classifier algorithm based on a perturbation method and its application to ECG beat recognition systems. Expert Syst. Appl. 31:150–158, 2006.CrossRefGoogle Scholar
  3. 3.
    Akay, M., Wavelet application in medicine. IEEE Spectr. 34(5):50–56, 1997.CrossRefGoogle Scholar
  4. 4.
    Alickovic, E., and Subasi, A., Effect of Multiscale PCA de-noising in ECG beat classification for diagnosis of cardiovascular diseases. Circ. Syst. Sig. Process. 34(2):513–533, 2015. doi: 10.1007/s00034-014-9864-8.CrossRefGoogle Scholar
  5. 5.
    Andreao, R. V., Dorizzi, B., and Boudy, J., ECG signal analysis through hidden Markov models. IEEE Trans. Biomed. Eng. 53:1541–1549, 2006.CrossRefPubMedGoogle Scholar
  6. 6.
    Asl, B. M., Setarehdan, S. K., and Mohebbi, M., Support vector machine-based arrhythmia classification using reduced features of heart rate variability signal. Artif. Intell. Med. 44(1):51–64, 2008.CrossRefPubMedGoogle Scholar
  7. 7.
    Bakshi, B. R., Multiscale PCA with Application to Multivariate Statistical Process Monitoring. AIChE Journal. 44(7):1596–1610, 1998.Google Scholar
  8. 8.
    Breiman, L., Random forests. Mach. Learn. 45:5–32, 2001.CrossRefGoogle Scholar
  9. 9.
    Castillo, O., Melin, P., Ramírez, E., and Soria, J., Hybrid intelligent system for cardiac arrhythmia classification with Fuzzy K-Nearest Neighbors and neural networks combined with a fuzzy system. Expert Syst. Appl. 39(3):2947–2955, 2012.CrossRefGoogle Scholar
  10. 10.
    Chazal, P. d., O’Dwyer, M., and Reilly, R. B., Automatic classification of heartbeats using ECG morphology and heartbeat interval features. IEEE Trans. Biomed. Eng. 51(7):1196–1206, 2004.CrossRefPubMedGoogle Scholar
  11. 11.
    Cho, G.-Y., Lee, S.-J., and Lee, T.-R., An optimized compression algorithm for real-time ECG data transmission in wireless network of medical information systems. J. Med. Syst. 39(161), 2015.Google Scholar
  12. 12.
    Daqrouq, K., Alkhateeb, A., Ajour, M. N., and Morfeq, A., Neural network and wavelet average framing percentage energy for atrial fibrillation classification. Comput. Methods Prog. Biomed. 113(3):919–926, 2014.CrossRefGoogle Scholar
  13. 13.
    Díaz-Uriarte, R., & Alvarez de Andrés, S., Gene selection and classification of microarray data using random forest. BMC Bioinforma. 2006Google Scholar
  14. 14.
    Dingfei, G., Srinivasan, N., & Krishnan, S. M., Cardiac arrhythmia classification using autoregressive modeling. BioMed. Eng. OnLine. 1(5). doi: 10.1186/1475-925X-1-5 2002.
  15. 15.
    Goldberger, A., Amaral, L. A., Glass, L., Hausdorff, J. M., Ivanov, P. C., Mark, R. G., . . . Stanley, H. E., PhysioBank, PhysioToolkit, and PhysioNet: Components of a New Research Resource for Complex Physiologic Signals. Circulation, 101(23), 215–220. Retrieved from 2000.
  16. 16.
    Hastie, T., Tibshirani, R., & Friedman, J. . The elements of statistical learning: data mining, ınference, and prediction (2nd ed.). Springer, 2009.Google Scholar
  17. 17.
    Homaeinezhad, M. R., Atyabi, S. A., Tavakkoli, E., Toosi, H. N., Ghaffari, A., and Ebrahimpour, R., ECG arrhythmia recognition via a neuro-SVM–KNN hybrid classifier with virtual QRS image-based geometrical features. Expert Syst. Appl. 39:2047–2058, 2012.CrossRefGoogle Scholar
  18. 18.
    Hosseini, H. G., Reynolds, K. J., & Powers, D., A multi-stage neural network classifier for ECG events. 23rd Int. Conf. IEEE EMBS, 2, pp 1672–1675, 2001.Google Scholar
  19. 19.
    Hu, G. M., Palreddy, S., and Tompkins, W., Patient adaptable ECG beat classifier using a mixture of experts approach. IEEE Trans. Biomed. Eng. 44:891–900, 1997.CrossRefPubMedGoogle Scholar
  20. 20.
    Kandaswamy, A., Kumar, C. S., Ramanathan, R. P., Jayaraman, S., and Malmurugan, N., Neural classification of lung sounds using wavelet coefficients. Comput. Biol. Med. 34(6):523–537, 2004.CrossRefPubMedGoogle Scholar
  21. 21.
    Kevric, J., and Subasi, A., The effect of multiscale PCA de-noising in epileptic seizure detection. J. Med. Syst. 38(131):1–13, 2014. doi: 10.1007/s10916-014-0131-0.Google Scholar
  22. 22.
    Khazaee, A., and Ebrahimzadeh, A., Classification of electrocardiogram signals with support vector machines and genetic algorithms using power spectral features. Biomed. Signal Process Control. 5:252–263, 2010.CrossRefGoogle Scholar
  23. 23.
    Korurek, M., and Dogan, B., ECG beat classification using particle swarm optimization and radial basis function neural network. Expert Syst. Appl. 37(12):7563–7569, 2010.CrossRefGoogle Scholar
  24. 24.
    Krummen, D. E., Patel, M., Nguyen, H., Ho, G., Kazi, D. S., and Clopton, P., Accurate ECG diagnosis of atrial tachyarrhythmias using quantitative analysis: a prospective diagnostic and cost-effectiveness study. J. Cardiovasc. Electrophysiol. 21(11):1251–1259, 2010.CrossRefPubMedPubMedCentralGoogle Scholar
  25. 25.
    Lagerholm, M., Clustering ECG complexes using Hermite functions and self-organizing maps. IEEE Trans. Biomed. Eng. 47:839–847, 2000.CrossRefGoogle Scholar
  26. 26.
    Lazarevic-McManus, N., Renno, J. R., Makris, D., and Jones, G. A., An object-based comparative methodology for motion detection based on the F-Measure. Comput. Vis. Image Underst. 111:74–85, 2008.CrossRefGoogle Scholar
  27. 27.
    Lewis, R. J., An Introduction to Classification and Regression Tree (CART) Analysis. Annual Meeting of the Society for Academic Emergency Medicine. San Francisco, California. 2000.Google Scholar
  28. 28.
    Lin, C. H., Frequency-domain features for ECG beat discrimination using grey relational analysis based classifier. Comput. Math. Appl. 55:680–690, 2008.CrossRefGoogle Scholar
  29. 29.
    Lin, B.-S., Wong, A. M., and Tseng, K. C., Community-based ECG monitoring system for patients with cardiovascular diseases. J. Med. Syst. 2016. doi: 10.1007/s10916-016-0442-4.Google Scholar
  30. 30.
    Martis, R. J., Chakraborty, C., and Ray, A. K., A two-stage mechanism for registration and classification of ECG using Gaussian mixture model. Pattern Recogn. 42(11):2979–2988, 2009.CrossRefGoogle Scholar
  31. 31.
    Martis, R. J., Acharya, U. R., Mandana, K. M., Ray, A. K., and Chakraborty, C., Application of principal component analysis to ECG signals for automated diagnosis of cardiac health. Expert Syst. Appl. 39:11792–11800, 2012.CrossRefGoogle Scholar
  32. 32.
    Martis, R., Krishnan, M. M., Chakraborty, C., Pal, S., Sarkar, D., Mandana, K. M., and Ray, A. K., Automated screening of arrhythmia using wavelet based machine learning techniques (Article). J. Med. Syst. 36(2):677–688, 2012.CrossRefPubMedGoogle Scholar
  33. 33.
    Martisa, R. J., Acharya, U. R., and Min, L. C., ECG beat classification using PCA, LDA, ICA and discrete wavelet transform. Biomed. Signal Process. Control. 8(5):437–448, 2013.CrossRefGoogle Scholar
  34. 34.
    Melgani, F., and Bazi, Y., Classification of electrocardiogram signals with support vector machines and particle swarm optimization. IEEE Trans. Inf. Technol. Biomed. 12(5):667–677, 2008.CrossRefPubMedGoogle Scholar
  35. 35.
    Melin, P., Amezcua, J., Valdez, F., and Castillo, O., A new neural network model based on the LVQ algorithm for multi-class classification of arrhythmias. Inf. Sci. 279:483–497, 2014.CrossRefGoogle Scholar
  36. 36.
    MIT-BIH Arrhythmia Database Directory., Retrieved May 2, 2012, from MIT-BIH Arrhythmia Database Directory: 2001.
  37. 37.
    Moavenian, M., and Khorrami, H., A qualitative comparison of artificial neural networks and support vector machines in ECG arrhythmias classification. Expert Syst. Appl. 37:3088–3093, 2010.CrossRefGoogle Scholar
  38. 38.
    Pan, J., and Tompkins, W. J., A real-time QRS detection algorithm. IEEE Trans. Biomed. Eng. BME-32(3):230–236, 1985.CrossRefGoogle Scholar
  39. 39.
    Polat, K., and Güneş, S., A novel data reduction method: distance based data reduction and its application to classification of epileptiform EEG signals. Appl. Math. Comput. 200(1):10–27, 2008.Google Scholar
  40. 40.
    Rijsbergen, R. V., Information retrieval (2nd ed.). Department of Computing Science, University of Glasgow. 1979. Accessed from:
  41. 41.
    Ripley, B. D., Pattern recognition and neural networks. Cambridge University Press, Cambridge, 1996.CrossRefGoogle Scholar
  42. 42.
    Sarvestani, R. R., Boostani, R., and Roopaei, M., VT and VF classification using trajectory analysis. Nonlinear Anal. 2008. doi: 10.1016/ Scholar
  43. 43.
    Semmlow, J. L., Biosignal and biomedical ımage processing - MATLA B-Based Applications. Marcel Dekker, 2004.Google Scholar
  44. 44.
    Senhadji, L., Carrault, G., Bellanger, J.J., and Passariello, G., Comparing wavelet transforms for recognizing cardiac patterns. IEEE Eng. Med. Biol. 14(2):167–173, 1995.CrossRefGoogle Scholar
  45. 45.
    Shen, C.-P., Kao, W.-C., Yang, Y.-Y., Hsu, M.-C., Wu, Y.-T., and Lai, F., Detection of cardiac arrhythmia in electrocardiograms using adaptive feature extraction and modified support vector machines. Expert Syst. Appl. 39:7845–7852, 2012.CrossRefGoogle Scholar
  46. 46.
    Shyu, L. Y., Wu, Y. H., and Hu, W. C., Using wavelet transform and fuzzy neural network for VPC detection from the Holter ECG. IEEE Trans. Biomed. Eng. 51:1269–1273, 2004.CrossRefPubMedGoogle Scholar
  47. 47.
    St.-Petersburg Institute of Cardiological Technics 12-lead Arrhythmia Database., Retrieved Februare 6, 2015, from PhysioBank: 2015.
  48. 48.
    Subasi, A., Automatic recognition of alertness level from EEG by using neural network and wavelet coefficients. Expert Syst. Appl. 28:701–711, 2005.CrossRefGoogle Scholar
  49. 49.
    Subasi, A., EEG signal classification using wavelet feature extraction and a mixture of expert model. Expert Syst. Appl. 32:1084–1093, 2007.CrossRefGoogle Scholar
  50. 50.
    Subasi, A., Medical decision support system for diagnosis of neuromuscular disorders using DWT and fuzzy support vector machines. Comput. Biol. Med. 42(8):806–815, 2012.CrossRefPubMedGoogle Scholar
  51. 51.
    Subasi, A., Classification of EMG signals using PSO optimized SVM for diagnosis of neuromuscular disorders. Comput. Biol. Med. 43(5):576–586, 2013. doi: 10.1016/j.compbiomed.2013.01.020.CrossRefPubMedGoogle Scholar
  52. 52.
    Subasi, A., and Gursoy, M. I., EEG signal classification using PCA, ICA, LDA and support vector machines. Expert Syst.Appl. 37(12):8659–8666, 2010.CrossRefGoogle Scholar
  53. 53.
    Thaler, M. S., The only EKG book you’ll ever need, vol. 3. Lippincott Williams & Wilkins, Philadelphia, 1999.Google Scholar
  54. 54.
    Witten, I. H., and Frank, E., Data mining practical machine learning tools and techniques, 2nd edition. Elsevier Inc, San Francisco, 2005.Google Scholar
  55. 55.
    Yeh, Y.-C., Wang, W.-J., and Chiou, C. W., A novel fuzzy c-means method for classifying heartbeat cases from ECG signals. Measurement 43:1542–1555, 2010.CrossRefGoogle Scholar
  56. 56.
    Yeh, Y. C., Chiou, C. W., and Lin, H.-J., Analyzing ECG for cardiac arrhythmia using cluster analysis. Expert Syst. Appl. 39:1000–1010, 2012.CrossRefGoogle Scholar
  57. 57.
    Yu, S.-N., and Chou, K.-T., A switchable scheme for ECG beat classification based on independent component analysis. Expert Syst. Appl. 33:824–829, 2007.CrossRefGoogle Scholar
  58. 58.
    Yu, S. N., and Chou, K. T., Selection of significant independent components for ECG beat classification. Expert Syst. Appl. 38(2):2088–2096, 2009.CrossRefGoogle Scholar
  59. 59.
    Zade, A. E., Khazaee, A., and Ranaee, V., Classification of the electrocardiogram signals using supervised classifiers and efficient features. Comput. Methods Prog. Biomed. 99:179–194, 2010.CrossRefGoogle Scholar
  60. 60.
    Zidelmal, Z., Amirou, A., Ould-Abdeslamb, D., and Merckleb, J., ECG beat classification using a cost sensitive classifier. Comput. Methods Prog. Biomed. 11(3):570–577, 2013.CrossRefGoogle Scholar
  61. 61.
    Zweig, M. H., and Campbell, G., Receiver-operating characteristic (ROC) plots: a fundamental evaluation tool in clinical medicine. Clin. Chem. 39(4):561–577, 1993.PubMedGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2016

Authors and Affiliations

  1. 1.Department of Electrical EngineeringLinkoping UniversityLinkopingSweden
  2. 2.College of EngineeringEffat UniversityJeddahSaudi Arabia

Personalised recommendations