Biological Sources of Seismocardiographic Signals

Seismocardiographic (SCG) signals are the acoustic and vibration induced by cardiac activity measured non-invasively at the chest surface. These signals may offer a method for diagnosing and monitoring heart function. Successful classification of SCG signals in health and disease depends on accurate signal characterization and feature extraction.

As opposed to other biological signals such as electrocardiograms and heart sounds, SCG signals are not well understood yet. Thus, understanding the genesis and biological sources of these signals is among the first steps before we can use them for diagnosis purposes.

Objective

Investigate the biological and pathological sources of the cardiovascular-induced sounds and vibrations measured noninvasively on the body surface

Skillsets

Signal and image processing
Machine learning
Computational fluid dynamics and finite element modeling

Key Finding

We discovered that SCG waveforms (corresponding to cardiac cycles) change in both time and frequency domains with the lung volume, i.e. when the lung is empty versus filled with the inhaled air. Our results showed that SCG events tended to have two slightly different morphologies. This finding resulted in grouping the SCG events into clusters where the events in each cluster were more similar to each other.

Selected Publications

2019 - Vibration

Recent Advances in Seismocardiography

Cardiovascular disease is a major cause of death worldwide. New diagnostic tools are needed to provide early detection and intervention to reduce mortality and increase both the duration and quality of life for patients with heart disease. Seismocardiography (SCG) is a technique for noninvasive evaluation of cardiac activity. However, the complexity of SCG signals introduced challenges in SCG studies. Renewed interest in investigating the utility of SCG accelerated in recent years and benefited from new advances in low-cost lightweight sensors, and signal processing and machine learning methods. This paper reviews the recent advances in the field of SCG.

2020 - Signal Processing in Medicine and Biology

Clustering of SCG Events using Unsupervised Machine Learning

Variability in SCG morphology impedes the precise determination of average waveforms. Hence, it is desirable to group SCG beats into clusters with minimal intra-cluster heterogeneity.

Other Publications

Sandler, R.H., Azad, M.K., Rahman, B., Taebi, A., Gamage, P., Raval, N., Mentz, R.J., Mansy, H.A. (2019). Minimizing Seismocardiography Variability by Accounting for Respiratory Effects. Journal of Cardiac Failure 25(8): S172.
doi 10.1016/j.cardfail.2019.07.521
Gamage, P.T., Azad, M.K., Taebi, A., Sandler, R.H., Mansy, H.A. (2018). Clustering Seismocardiographic Events using Unsupervised Machine Learning. IEEE Signal Processing in Medicine and Biology, Philadelphia (PA).
doi 10.1109/SPMB.2018.8615615
Taebi, A., Mansy, H.A. (2017) Grouping Similar Seismocardiographic Signals Using Respiratory Information, IEEE Signal Processing in Medicine and Biology, Philadelphia (PA).
doi 10.1109/SPMB.2017.8257053

Full list of publications in Google Scholar