High-Accuracy, Unsupervised Annotation of Seismocardiogram Traces for Heart Rate Monitoring

This article presents an unsupervised, automated procedure for the analysis of Seismocardiogram (SCG) signals. SCG is a measure of chest vibrations, induced by the mechanical activity of the heart, which allows extracting relevant parameters, including heart rate (HR) and HR variability (HRV). An initial self-calibration is performed, solely based on the SCG traces, yielding a suitable heartbeat template (personalized for each subject). Then, beat detection and timing annotation are performed in two steps: at first, candidate beats are identified and validated, by means of suitably defined detection signals; then, precise timing annotation is achieved by best aligning such candidate beats to the previously extracted template. The algorithm has been validated on two separate data sets, featuring different acquisition setups: the first one is the publicly available Combined measurement of ECG, Breathing and Seismocardiogram (CEBS) database, reporting SCG signals from the subjects lying in supine position, whereas the second one was acquired using a custom setup, involving the sitting subjects. Results show good sensitivity and precision scores (98.5% and 98.6% for the CEBS database, and 99.1% and 97.9% for the Custom one, respectively). In addition, comparison with electrocardiogram (ECG) gold-standard is given, showing good agreement between the beat-to-beat intervals computed from SCG and the ECG gold-standard: on average, $R^{2}$ scores of 99.3% and 98.4% are achieved on the CEBS and Custom data sets, respectively. Furthermore, a low rms error is achieved on the CEBS and Custom data sets, amounting to 4.6 and 6.2 ms, respectively (i.e., $2.3\;T_{s}$ and $3.1\;T_{s}$ , where $T_{s}$ is the sampling period): such results are well compared with related literature. Validation on two different data sets indicates the robustness of the proposed methodology.