Quality Assessment of 12-Lead ECG in Body Sensor Network

Author(s): Amal N. El-Sari, Reda A. El-Khoribi

Body sensor network (BSN) is simple and effective biophysical data capture in real time to monitor human activities, such as health status and physiological signals for a wide range of application area. Electrocardiogram (ECG) uses medical body sensors to record the electrical activity of the heart to help diagnose of heart disease, and also monitor how well different heart medications are working. ECG is usually by affected by various types of noises. The most common noises originated from the power line interference, electrodes loss contact, baselines wander and motion artifact. This paper introduces a new technique for improving the quality of ECG using multi scale quantitive recurrence analysis (QRA) for feature extraction and decision tree classifier. The approach achieved classification accuracy of 92.4%, when tested on a dataset from the Computing in cardiology/PhysioNet Challenge 2011.

BSN, ECG, QRA, Decision tree

1. Jones V., Gay V. and Leijdekkers P. “Body Sensor Networks for Mobile Health Monitoring” Fourth International Conference on Digital Society: Icds Proceedings, 204-209, 2010
2. Otto C., Milenkovic A., Sanders C., and Jovanov E. “System architecture of a wireless body area sensor network for ubiquitous health monitoring” Journal of Mobile Multimedia, vol. 1, no. 4, pp. 307–326, Jan. 2006
3. Silva I., Moody G. B. and Celi L. “Improving the quality of ECGs collected using mobile phones”: the PhysioNet/computing in cardiology challenge Comput. Cardiol. 38 273–6, 2011
4. Tat T. H C, Xiang C. and Thiam L E. “Physionet challenge 2011: improving the quality of electrocardiography data collected using real time QRS-complex and T-wave detection” Comput. Cardiol. 38 441–4 , 2012
5. Chen and Yang. “Self-organized neural network for the quality control of 12-lead ECG signals” Comput. Cardiol 2012
6. Zaunseder S., Huhle R. and Malberg H. “Assessing the usability of ECG by ensemble decision trees”, Comput. Cardiol. 2012
7. Clifford G D, Lopez D, Li Q and Rezek I “Signal quality indices and data fusion for determining acceptability of electrocardiograms collected in noisy ambulatory environments” Comput. Cardiol. 38 285–8, 2012
8. Redmond S J, Xie Y, Chang D, Basilakis J and Lovell N H., ”Electrocardiogram signal quality measures forunsupervised telehealth environments,” Comput. Cardiol. 2012
9. Jekova I, Krasteva V, Dotsinsky I, Christov I and Abacherli R “Recognition of diagnostically useful ECG recordings: Alert for corrupted or interchanged leads” Comput. Cardiol. 38 429–32, 2012
10. Johannesen L., “Assessment of ECG quality on an Android platform,” Comput. Cardiol. 38 433–6, 2012
11. Hayn D, Jammerbund B. and Schreier G., “ECG quality assessment for patient empowerment in mHealth Applications,” Comput. Cardiol. 38 353–6, 2012
12. Kalkstein N, Kinar Y, Na’aman M, Neumark N and Akiva P., “Using machine learning to detect problems in ECG data collection,” Comput. Cardiol. 38 437–40, 2012
13. Langley P., Marco L Y D., King S., Duncan D., Maria C D., Duan W., Bojarnejad M, Zheng D, Allen J and Murray A., “An algorithm for assessment of quality of ECGs acquired via mobile telephones,” Comput. Cardiol 38 281–4, 2012
14. Dower G E, Yakush A, Nazzal S B, Jutzy R V and Ruiz C E “Deriving the 12-lead electrocardiogram from four (EASI) electrodes” J. Electrocardiol. 21 (Suppl 1) S182–7,1988
15. Burrus, R.A. Gopinath, H. Guo, “Introduction to Wavelets and Wavelet. Transforms”, a Primer, Prentice Hall Inc. 1997
16. Rioul O. and Vetterli M., “Wavelets and signal processing,” IEEE Signal Processing Magazine, vol. 8, no. 4, Oct. pp. 14-38, 1991
17. Webber C.L., Jr. “Introduction to recurrence quantification analysis” 2004
18. Webber C L. and Zbilut J P, “Dynamical assessment of physiological systems and states using recurrence plot strategies,” J. Appl. Physiol. 76 965–73, 1994
19. Marwan N., Carmen Romano M., Thiel M and Kurths J ., “Recurrence plots for the analysis of complex systems,” Phys. Rep. 438 237–329, 2007
20. Yang H “Multiscale recurrence quantification analysis of spatial cardiac vectorcardiogram (VCG) signals” IEEE Trans. Biomed. Eng. 58 339–47,2011
21. Quinlan R., “Induction of Decision Trees,” Machine Learning, Vol. 81—106, 1986
22. Breiman, L., et al., “Classification and Regression Trees,” Chapman & Hall, Boca Raton, 1993
23. Efron, B., “Estimating the error rate of a prediction rule: Improvement on cross-validation.” Journal of the American Statistical Association, Vol. 78, 316-331.1983
24. Byon, E., Shrivastava, A. K., and Ding, Y., “A classification procedure for highly imbalanced class sizes,” IIE Transactions, Vol. 42, No. 4, pp. 288-303, 2010