Reconstruction of 3-Axis Seismocardiogram from Right-to-left and Head-to-foot Components Using A Long Short-Term Memory Network

This pilot study aims to develop a deep learning model for predicting seismocardiogram (SCG) signals in the dorsoventral direction from the SCG signals in the right-to-left and head-to-foot directions ($\textrm{SCG}_x$ and $\textrm{SCG}_y$). The dataset used for the training and validation of the model was obtained from 15 healthy adult subjects. The SCG signals were recorded using tri-axial accelerometers placed on the chest of each subject. The signals were then segmented using electrocardiogram R waves, and the segments were downsampled, normalized, and centered around zero. The resulting dataset was used to train and validate a long short-term memory (LSTM) network with two layers and a dropout layer to prevent overfitting. The network took as input 100-time steps of $\textrm{SCG}_x$ and $\textrm{SCG}_y$, representing one cardiac cycle, and outputted a vector that mapped to the target variable being predicted. The results showed that the LSTM model had a mean square error of 0.09 between the predicted and actual SCG segments in the dorsoventral direction. The study demonstrates the potential of deep learning models for reconstructing 3-axis SCG signals using the data obtained from dual-axis accelerometers.

Effect of Measurement Location on Cardiac Time Intervals Estimated by Seismocardiography

Cardiac time intervals (CTIs) are important parameters for assessing cardiac function and can be measured using non-invasive methods such as electrocardiography (ECG) and seismocardiography (SCG). It is widely accepted that SCG signals, when measured from various locations on the chest surface, exhibit distinct temporal and spectral characteristics. In that regard, the goal of this study was to determine the effect of the SCG measurement location on estimating SCG-based CTIs. For this purpose, ECG, SCG, and phonocardiography (PCG) signals were acquired from fourteen healthy adult subjects. For SCG, three tri-axial accelerometers were attached on the top, middle, and bottom of the sternum with double-sided tape. In this study, only the dorsoventral components of the SCG signals were analyzed. Using Pan-Tompkin's algorithm, ECG R peaks and their temporal indices were found. Then, a custom-built algorithm in MATLAB was developed to estimate heart rate (HR) from ECG and SCG signals. Furthermore, SCG fiducial points and CTIs were defined from the SCG signals recorded from different sternal locations. The average and correlation coefficient of the CTIs and HRs derived from all three locations were compared. Mean difference and standard deviation were analyzed for the CTIs and their respective sensor location. Results demonstrated that SCG-based CTIs varied with the SCG measurement locations. In conclusion, these results highlighted the importance of establishing consistent research and clinical protocols for reporting CTIs based on SCG. This work also calls for further investigation into comparing estimated CTIs with gold-standard methods such as echocardiography and 4D cardiac computed tomography.