Development of an Algorithm for Clustering Cardiac ECG Signals with Post-Correction for Long-Term ECG Monitoring

Introduction. The most common method for diagnosing cardiovascular diseases is the method of ECG monitoring. In order to facilitate the analysis of the obtained monitorograms, special software solutions for automated ECG processing are required. One possible approach is the use of algorithms for automated ECG processing. Such algorithms perform  clustering of cardiac signals by dividing the ECG into complexes of similar cardiac signals. The most representative complexes obtained by statistical averaging are subject to further analysis.

Aim. Development of an algorithm for automated ECG processing,  which performs clustering of cardiac signals by dividing the ECG into complexes of similar cardiac signals.

Materials and methods. Experimental testing of the developed software was carried out using patient records provided by the Pavlov First State Medical University of St  Petersburg. The software module was implemented in the MatLab environment.

Results. An algorithm for clustering cardiac signals with post-correction for the tasks of long-term ECG monitoring and a software module on its basis were proposed.

Conclusion.  The presence of a small number of reference cardiac signal complexes, obtained through ECG processing using the proposed algorithm, allows physicians to optimize the process of ECG analysis. The as- obtained information serves as a basis for assessing dynamic changes in the shape and other parameters of cardiac signals for both a particular patient and groups of patients. The paper considers the effect of synchronization errors of clustered cardiac signals on the shape of the averaged cardiac complex. The classical solution to the deconvolution problem leads to significant errors in finding an estimate of the true form of a cardiac signal complex. On the basis of analytical calculations, expressions were obtained for the correction of clustered cardiac signals. Such correction was shown to reduce clusterization errors associated with desynchronization, which creates a basis for investigating the fine structure of ECG signals.

1. Krasichkov A. S., Nifontov E. M., Ivanov V. S. Classi fication algorithm for complexes in long term ECG data records. Biomedical Radio Electronics. 2011, no. 11, pp. 24–28. (In Russ.)

2. Siddiah N., Srikanth T., Satish Kumar Y. Nonlinear filtering in ECG Signal Enhancement. Intern. J. of Computer Science and Communication Networks. 2012, vol. 2, iss. 1, pp. 123–128. Available at: https://www.researchgate.net /publication/268435345_Nonlinear_filtering_in_ECG_Signal _Enhancement (accessed 2021/02/26)

3. Hao W., Chen Y., Xin Y. ECG Baseline Wander Correction by Meanmedian Filter and Discrete Wavelet Transform. 2011 Annual Intern. Conf. of the IEEE Engineering in Medicine and Biology Society. 30 Aug.–3 Sept. 2011, Boston, USA.Piscataway, IEEE, 2011, acc. no. 12424657. doi: 10.1109 /IEMBS.2011.6090744

4. Verma R., Mehrotra R., Bhateja V. An Integration of Improved Median and Morphological Filtering Techniques for Electrocardiogram Signal Processing. 2013 3rd IEEE Intern. Advance Computing Conf. (IACC). 22–23 Febr. 2013, Ghaziabad, India. Piscataway, IEEE,2013, pp. 1223–1228. doi: 10.1109/IAdCC.2013.6514402

5. Ji T. Y., Lu Z., Wu Q. H., Ji Z. Baseline Normalization of ECG Signals using Empirical Mode Decomposition and Mathematical Morphology. Electronic Lett. 2010, vol. 43, no. 6, pp. 486 – 496

6. Pipin V. V., Ragulskaya M. V., Chibisov S. M. Analysis of dynamic models and ECG reconstructions under the influence of cosmo - and geophysical factors. J. of Applied and Fundamental Research. Technical sciences. 2009, no. 5. pp. 17– 24. (In Russ.)

7. Al-Kindi S. G., Reza T. Real-time Detection of Myocardial Infarction by Evaluation of ST-segment in Digital ECG. J. of Medical Imaging and Health Informatics. 2011, vol. 1, iss. 3, pp. 225–230. doi: 10.1166/jmihi.2011.1032

8. Kondratyeva I. A., Krasichkov A. S., Nifontov E. M., Shikama F. Analysis of the Possibility of Correcting the Shape of the Average Cardiac Complex in the Presence of Synchronization Errors during Accumulation. Intern. Youth Conf. on Electronics, Telecommunications and Information Technologies. Springer Proceedings in Physics. Cham, Springer, 2020, vol. 255, pp. 487–494. doi: 10.1007/978-3-030-58868-7_53I

9. Hsiao C.-C., Hsu F.-W., Lee R.-G., Lin R. Correlation Analysis of heart Rate Variability between PPG and ECG for Wearable Devices in Different Postures. 2017 IEEE Intern. Conf. on Systems, Man, and Cybernetics (SMC). 5–8 Oct. 2017, Banff, AB. Piscataway, IEEE, 2013, acc. no. 17379519. doi: 10.1109/SMC.2017.8123077

10. Kan Y., Kashihara K. Automatic Detection of ST Depression on ECG. 2015 IEEE 4th Global Conf. on Consumer Electronics (GCCE). 27–30 Oct. 2015, Osaka, Japan. Piscataway, IEEE, 2015, acc. no. 15756665. doi: 10.1109/GCCE.2015.7398704

11. Hammond H. K., Kelly T. L., Froelicher V. Radionuclide Imaging Correlatives of Heart Rate Impairment during Maximal Exercise Testing. J. of the American College of Cardiology. 1983, vol. 2, no 5, pp. 826 –833. doi: 10.1016/s0735-1097(83)80228-911

12. Krasichkov A. S., Grigoriev E. B., Nifontov E. M. Influence of Myographic Interference and Isoelectric Line Drift on Correlation Coefficient in Classification of Cardiocomplexes. Biomedical Engineering. 2015, vol. 49, iss. 4, pp. 220–223. doi: 10.1007/s10527-015-9533-7

13. O’Connor J. M., Pretorius P. H., Johnson K., King M. A. A method to Synchronize Signals from Multiple Patient Monitoring Devices through a Single Input Channel for Inclusion in List-mode Acquisitions. Medical Physics. 2013, vol. 40, iss. 12, art. 122502. doi: 10.1118/1.4828844

14. Pathoumvanh S., Hamamoto K., Indahak P. Arrhythmias Detection and Classification Base on single Beat ECG Analysis. The 4 th Joint Intern. Conf. on Information and Communication Technology, Electronic and Electrical Engineering (JICTEE). Chiang Rai, Thailand. 5–8 Mar. 2014,acc. no. 14255947, 4 p. doi: 10.1109/JICTEE.2014.6804097

15. Ma J. L., Zhang T. T., Dong M. C. A Novel ECG Data Compression Method using Adaptive Fourier Decomposition with Security Guarantee in E-health Applications. IEEE J. of Biomedical and Health Informatics. 2015, vol. 19, iss. 3, pp. 986–994. doi: 10.1109/JBHI.2014.2357841