Advertisement

Clustering of SCG Events Using Unsupervised Machine Learning

  • Peshala T. GamageEmail author
  • Md Khurshidul Azad
  • Amirtaha Taebi
  • Richard H. Sandler
  • Hansen A. Mansy
Chapter
  • 49 Downloads

Abstract

Seismocardiography (SCG) is the measurement of chest surface vibrations induced by cardiac activity. SCG beats are typically averaged to reduce noise and determine average SCG waveforms and features. Variability in SCG morphology impedes precise determination of average waveforms. Hence, it is desirable to group SCG beats into clusters with minimal intra-cluster heterogeneity. Cardio-pulmonary interactions are known to contribute to SCG variability. Therefore, grouping SCG signals by their respiratory phase may be helpful. SCG signals and respiratory flowrate were simultaneously measured in seventeen subjects (Age: 23 ± 3.5 years, 7 female). Unsupervised machine learning was implemented to cluster SCG beats according to their morphology. The time domain amplitudes of the SCG beats were used as the feature vector. K-medoids clustering was employed with dynamic time warping (DTW) distance as the heterogeneity measure. The quality of the clustering was measured using mean silhouette values and the elbow method for varying clusters numbers. Optimal clustering was achieved when SCG beats were split into two groups. Using respiratory flow information, SCG beats were labeled as inspiratory vs. expiratory, and as high vs. low lung volumes. The SCG groups determined by machine learning were compared with these labels. Grouping SCG based on lung volume phases yielded more homogeneous clusters than grouping by inspiration vs. expiration (p < 0.01). Unsupervised clustering reduced the intra-cluster variability by an average of 15% across subjects. Grouping by lung volume and inspiration vs. expiration reduced variability by 6% and 3%, respectively. The variability reduction may help more precise determination of average SCG waveforms and features, thereby improving SCG diagnostic utility.

Keywords

Seismocardiography Variability Unsupervised machine learning k-medoids Dynamic time warping 

Notes

Acknowledgements

This study was supported by NIH R44HL099053.

Hansen A. Mansy and Richard H. Sandler are part owners of Biomedical Acoustics Research Company, which is the primary recipient of the above grant, as such they may benefit financially as a result of the outcomes of the research work reported in this publication.

References

  1. 1.
    Gurev, V., Tavakolian, K., Constantino, J., Kaminska, B., Blaber, A. P., & Trayanova, N. A. (2012). Mechanisms underlying isovolumic contraction and ejection peaks in seismocardiogram morphology. Journal of Medical and Biological Engineering, 32(2), 103.CrossRefGoogle Scholar
  2. 2.
    Korzeniowska-Kubacka, I., Kuśmierczyk-Droszcz, B., Bilińska, M., Dobraszkiewicz-Wasilewska, B., Mazurek, K., & Piotrowicz, R. (2006). Seismocardiography-a non-invasive method of assessing systolic and diastolic left ventricular function in ischaemic heart disease. Cardiology Journal, 13(4), 319–325.Google Scholar
  3. 3.
    Taebi, A., Solar, B. E., Bomar, A. J., Sandler, R. H., & Mansy, H. A. (2019). Recent advances in seismocardiography. Vibration, 2(1), 64–86.CrossRefGoogle Scholar
  4. 4.
    Mounsey, P. (1957). Praecordial ballistocardiography. British Heart Journal, 19(2), 259.CrossRefGoogle Scholar
  5. 5.
    Bozhenko, B. (1961). Seismocardiography—a new method in the study of functional conditions of the heart. Terapevticheskiĭ Arkhiv, 33, 55.Google Scholar
  6. 6.
    Inan, O. T., Migeotte, P.-F., Park, K.-S., Etemadi, M., Tavakolian, K., Casanella, R., et al. (2015). Ballistocardiography and seismocardiography: a review of recent advances. IEEE Journal of Biomedical and Health Informatics, 19(4), 1414–1427.CrossRefGoogle Scholar
  7. 7.
    Wilson, R. A., Bamrah, V. S., Lindsay, J., Jr., Schwaiger, M., & Morganroth, J. (1993). Diagnostic accuracy of seismocardiography compared with electrocardiography for the anatomic and physiologic diagnosis of coronary artery disease during exercise testing. The American Journal of Cardiology, 71(7), 536–545.CrossRefGoogle Scholar
  8. 8.
    Di Rienzo, M., Meriggi, P., Rizzo, F., Vaini, E., Faini, A., Merati, G., et al. (2011). A wearable system for the seismocardiogram assessment in daily life conditions. In Paper presented at the 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.Google Scholar
  9. 9.
    Sahoo, P., Thakkar, H., Lin, W.-Y., Chang, P.-C., & Lee, M.-Y. (2018). On the design of an efficient cardiac health monitoring system through combined analysis of ECG and SCG signals. Sensors, 18(2), 379.CrossRefGoogle Scholar
  10. 10.
    Wick, C. A., Su, J.-J., McClellan, J. H., Brand, O., Bhatti, P. T., Buice, A. L., et al. (2012). A system for seismocardiography-based identification of quiescent heart phases: implications for cardiac imaging. IEEE Transactions on Information Technology in Biomedicine, 16(5), 869–877.CrossRefGoogle Scholar
  11. 11.
    Krishnan, K., Mansy, H., Berson, A., Mentz, R. J., & Sandler, R. H. (2018). Siesmocardiographic changes with HF status change: observations from a Pilot study. Journal of Cardiac Failure, 24(8), S54.CrossRefGoogle Scholar
  12. 12.
    Taebi, A., & Mansy, H. A. (2017a). Grouping similar seismocardiographic signals using respiratory information. In Paper presented at the signal processing in medicine and biology symposium (SPMB), 2017 IEEE.Google Scholar
  13. 13.
    Taebi, A. (2018), Characterization, classification, and genesis of seismocardiographic signals. Ph.D. Thesis, University of Central Florida, Orlando, FL, USA.Google Scholar
  14. 14.
    Taebi, A., & Mansy, H. A. (2017b). Time-frequency distribution of seismocardiographic signals: a comparative study. Bioengineering, 4(2), 32.CrossRefGoogle Scholar
  15. 15.
    Taebi, A., Solar, B. E., & Mansy, H. A. (2018). An adaptive feature extraction algorithm for classification of seismocardiographic signals. arXiv preprint arXiv:1803.10343.Google Scholar
  16. 16.
    Morillo, D. S., Ojeda, J. L. R., Foix, L. F. C., & Jiménez, A. L. (2010). An accelerometer-based device for sleep apnea screening. IEEE Transactions on Information Technology in Biomedicine, 14(2), 491–499.CrossRefGoogle Scholar
  17. 17.
    Reinvuo, T., Hannula, M., Sorvoja, H., Alasaarela, E., & Myllyla, R. (2006). Measurement of respiratory rate with high-resolution accelerometer and EMFit pressure sensor. In Paper presented at the Proceedings of the 2006 IEEE Sensors Applications Symposium, 2006.Google Scholar
  18. 18.
    Akhbardeh, A., Tavakolian, K., Gurev, V., Lee, T., New, W., Kaminska, B., et al. (2009). Comparative analysis of three different modalities for characterization of the seismocardiogram. In Paper presented at the Conference Proceedings.Google Scholar
  19. 19.
    Zanetti, J., Poliac, M., & Crow, R. (1991). Seismocardiography: Waveform identification and noise analysis. In Paper presented at the [1991] Proceedings Computers in Cardiology.Google Scholar
  20. 20.
    Zanetti, J. M., & Tavakolian, K. (2013). Seismocardiography: Past, present and future. In Paper presented at the 2013 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).Google Scholar
  21. 21.
    Khosrow-Khavar, F., Tavakolian, K., Blaber, A. P., Zanetti, J. M., Fazel-Rezai, R., & Menon, C. (2015). Automatic annotation of seismocardiogram with high-frequency precordial accelerations. IEEE Journal of Biomedical and Health Informatics, 19(4), 1428–1434.CrossRefGoogle Scholar
  22. 22.
    Sørensen, K., Schmidt, S. E., Jensen, A. S., Søgaard, P., & Struijk, J. J. (2018). Definition of fiducial points in the normal seismocardiogram. Scientific Reports, 8(1), 15455.CrossRefGoogle Scholar
  23. 23.
    Crow, R. S., Hannan, P., Jacobs, D., Hedquist, L., & Salerno, D. M. (1994). Relationship between seismocardiogram and echocardiogram for events in the cardiac cycle. American Journal of Noninvasive Cardiology, 8, 39–46.CrossRefGoogle Scholar
  24. 24.
    Tavakolian, K., Portacio, G., Tamddondoust, N. R., Jahns, G., Ngai, B., Dumont, G. A., et al. (2012). Myocardial contractility: a seismocardiography approach. In Paper presented at the Engineering in Medicine and Biology Society (EMBC), 2012 Annual International Conference of the IEEE.Google Scholar
  25. 25.
    Tavakolian, K., Vaseghi, A., & Kaminska, B. (2008). Improvement of ballistocardiogram processing by inclusion of respiration information. Physiological Measurement, 29(7), 771.CrossRefGoogle Scholar
  26. 26.
    Dai, Z., Peng, Y., Henry, B. M., Mansy, H. A., Sandler, R. H., & Royston, T. J. (2014). A comprehensive computational model of sound transmission through the porcine lung. The Journal of the Acoustical Society of America, 136(3), 1419–1429.CrossRefGoogle Scholar
  27. 27.
    Cheuk, M. Y., & Sanderson, J. E. (1997). Right and left ventricular diastolic function in patients with and without heart failure: effect of age, sex, heart rate, and respiration on Doppler-derived measurements. American Heart Journal, 134(3), 426–434.CrossRefGoogle Scholar
  28. 28.
    Gamage, P. T., Azad, M. K., Taebi, A., Sandler, R. H., & Mansy, H. A. (2018). Clustering seismocardiographic events using unsupervised machine learning. In Paper presented at the 2018 IEEE Signal Processing in Medicine and Biology Symposium (SPMB).Google Scholar
  29. 29.
    Solar, B. E., Taebi, A., & Mansy, H. A. (2017). Classification of seismocardiographic cycles into lung volume phases. In Paper presented at the Signal Processing in Medicine and Biology Symposium (SPMB), 2017 IEEE.Google Scholar
  30. 30.
    Zakeri, V., Akhbardeh, A., Alamdari, N., Fazel-Rezai, R., Paukkunen, M., & Tavakolian, K. (2017). Analyzing seismocardiogram cycles to identify the respiratory phases. IEEE Transactions on Biomedical Engineering, 64(8), 1786–1792.CrossRefGoogle Scholar
  31. 31.
    Tompkins, J. P. W. J. (1985). A real-time QRS detection algorithm. IEEE Transactions on Biomedical Engineering, BME-32(3), 230–236.  https://doi.org/10.1109/TBME.1985.325532.CrossRefGoogle Scholar
  32. 32.
    Paparrizos, J., & Gravano, L. (2017). Fast and accurate time-series clustering. ACM Transactions on Database Systems (TODS), 42(2), 8.MathSciNetCrossRefGoogle Scholar
  33. 33.
    Paparrizos, J., & Gravano, L. (2015). k-shape: Efficient and accurate clustering of time series. In Paper presented at the Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data.Google Scholar
  34. 34.
    Sakoe, H., & Chiba, S. (1978). Dynamic programming algorithm optimization for spoken word recognition. IEEE Transactions on Acoustics, Speech, and Signal Processing, 26(1), 43–49.zbMATHCrossRefGoogle Scholar
  35. 35.
    Silva, D. F., & Batista, G. E. (2016). Speeding up all-pairwise dynamic time warping matrix calculation. In Paper presented at the Proceedings of the 2016 SIAM International Conference on Data Mining.Google Scholar
  36. 36.
    Zhang, Z., Tang, P., Huo, L., & Zhou, Z. (2014). MODIS NDVI time series clustering under dynamic time warping. International Journal of Wavelets, Multiresolution and Information Processing, 12(05), 1461011.MathSciNetzbMATHCrossRefGoogle Scholar
  37. 37.
    Petitjean, F., Forestier, G., Webb, G. I., Nicholson, A. E., Chen, Y., & Keogh, E. (2014). Dynamic time warping averaging of time series allows faster and more accurate classification. In Paper presented at the Data Mining (ICDM), 2014 IEEE International Conference on.Google Scholar
  38. 38.
    Petitjean, F., Ketterlin, A., & Gançarski, P. (2011). A global averaging method for dynamic time warping, with applications to clustering. Pattern Recognition, 44(3), 678–693.zbMATHCrossRefGoogle Scholar
  39. 39.
    Rokach, L., & Maimon, O. (2005). Clustering methods data mining and knowledge discovery handbook (pp. 321–352). Berlin: Springer.zbMATHCrossRefGoogle Scholar
  40. 40.
    Von Luxburg, U. (2007). A tutorial on spectral clustering. Statistics and Computing, 17(4), 395–416.MathSciNetCrossRefGoogle Scholar
  41. 41.
    Zelnik-Manor, L., & Perona, P. (2005). Self-tuning spectral clustering. In Paper presented at the Advances in neural information processing systems.Google Scholar
  42. 42.
    Liao, T. W. (2005). Clustering of time series data—A survey. Pattern Recognition, 38(11), 1857–1874.zbMATHCrossRefGoogle Scholar
  43. 43.
    Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273–297.zbMATHGoogle Scholar
  44. 44.
    Angelone, A., & Coulter, N. A., Jr. (1964). Respiratory sinus arrhythmia: a frequency dependent phenomenon. Journal of Applied Physiology, 19(3), 479–482.CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Peshala T. Gamage
    • 1
    Email author
  • Md Khurshidul Azad
    • 1
  • Amirtaha Taebi
    • 2
  • Richard H. Sandler
    • 1
    • 3
  • Hansen A. Mansy
    • 1
    • 3
  1. 1.Biomedical Acoustic Research LabUniversity of Central FloridaOrlandoUSA
  2. 2.Department of Biomedical EngineeringUniversity of California DavisDavisUSA
  3. 3.Biomedical Acoustics Research CompanyOrlandoUSA

Personalised recommendations