Investigating the Effect of Body Composition Differences on Seismocardiogram Characteristics

In seismocardiogram (SCG) analysis, inter-subject variability is observed as the medium between the heart and accelerometer consists of different tissues made of bone, muscle, fat and skin cells of which combination varies across different people. Anatomically, a similar pattern is present in the speech production system, where the vocal cord and vocal tract are considered as the source and medium, respectively. For observing the change of the vocal tract filter while voicing different sounds, linear predictive analysis has been used for years. Thus, it was hypothesized that the medium characteristics of the human thorax would also have a filtering effect on the SCG signals and the differences in the filtering effects would be observed in the respiration (<1 Hz), vibration (1–20 Hz) and acoustic (>20 Hz) characteristics of the SCG signals. To that aim, three different binary classification tasks representing the body composition differences were defined: (i) whether the metabolic age of the subject is more than the real age of the subject, (ii) whether the BMI of the subject is bigger than 25, and (iii) whether the subject is male or female. To understand the metabolism-induced changes in the respiration, vibration and acoustic components, classification experiments were conducted using different frequency bands of the SCG signal. In each case, linear predictive coefficients were extracted and used to train individual classification models for the aforementioned scenarios. With the vibration components (1–20 Hz), all of the tasks resulted in high performance (0.86, 0.93, 0.93) for age, BMI and gender classification tasks, respectively. This study reveals that the vibration components of SCG make a stable and informative contribution to selected classification tasks, and due to its high generalizability, it is suitable for various practical applications.