Medical Decision Support System for Diagnosis of Heart Arrhythmia using DWT and Random Forests Classifier
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).
KeywordsElectrocardiogram (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.
- 7.Bakshi, B. R., Multiscale PCA with Application to Multivariate Statistical Process Monitoring. AIChE Journal. 44(7):1596–1610, 1998.Google Scholar
- 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
- 13.Díaz-Uriarte, R., & Alvarez de Andrés, S., Gene selection and classification of microarray data using random forest. BMC Bioinforma. 2006Google Scholar
- 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.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 http://circ.ahajournals.org/cgi/content/full/101/23/e215. 2000.
- 16.Hastie, T., Tibshirani, R., & Friedman, J. . The elements of statistical learning: data mining, ınference, and prediction (2nd ed.). Springer, 2009.Google Scholar
- 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
- 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
- 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
- 36.MIT-BIH Arrhythmia Database Directory., Retrieved May 2, 2012, from MIT-BIH Arrhythmia Database Directory: http://www.physionet.org/physiobank/database/html/mitdbdir/mitdbdir.htm. 2001.
- 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.Rijsbergen, R. V., Information retrieval (2nd ed.). Department of Computing Science, University of Glasgow. 1979. Accessed from: http://www.dcs.gla.ac.uk/Keith/Preface.html.
- 43.Semmlow, J. L., Biosignal and biomedical ımage processing - MATLA B-Based Applications. Marcel Dekker, 2004.Google Scholar
- 47.St.-Petersburg Institute of Cardiological Technics 12-lead Arrhythmia Database., Retrieved Februare 6, 2015, from PhysioBank: http://www.physionet.org/pn3/incartdb/ 2015.
- 53.Thaler, M. S., The only EKG book you’ll ever need, vol. 3. Lippincott Williams & Wilkins, Philadelphia, 1999.Google Scholar
- 54.Witten, I. H., and Frank, E., Data mining practical machine learning tools and techniques, 2nd edition. Elsevier Inc, San Francisco, 2005.Google Scholar