<h3>Introduction</h3> Seismocardiography signals (SCG) are acoustic vibrations generated by heart activity and measured non-invasively at the chest surface. The potential utility of SCG for HF diagnosis and monitoring may be limited by signal variability. Respiration is a known, yet not well understood, source of variability. The objective of this pilot study was to quantify the SCG variability during breathing maneuvers. <h3>Methods</h3> SCG, electrocardiography (ECG) and airflow signals were acquired in two healthy subjects during normal breathing and breath holding (at end-inspiration and end-expiration while the glottis remained open). Data recording was repeated three times, while subjects resting on a 45 degree-elevated tilt table. The SCG events were detected and segmented utilizing the ECG R wave. Although the waveform varied, using unsupervised machine learning (k-medoid clustering) one could separate SCG waveforms during breathing into two "clusters" of similar events. The SCG variability was calculated using Dynamic Time Warping (DTW). The time interval between SCG1 and SCG 2 (which corresponds to the heart-sound ejection-period or HSEP) was also calculated. <h3>Results</h3> Table 1 shows the mean and standard deviation (SD) of the following SCG features: intra-cluster variability, inter-session variability and HSEP during regular breathing, breath hold at end inspiration and end expiration. SCG average intra-cluster and inter session variability was 27% and 24% lower, respectively, during breath holding for both end-inspiration and end-expiration compared to normal breathing. In addition, HSEP was 12% lower during breath holding compared to normal breathing. <h3>Conclusion</h3> Appropriate accounting for SCG variability introduced by breathing appears to account for a significant portion of the signal variability. Hence algorithms integrating respiratory changes may lead to more robust SCG analysis for HF diagnosis and monitoring. In addition, the observed respiration-dependent variability may prove to be a useful feature for HF management. Further studies are needed to confirm these findings in HF patients.