Key result
U-Net deep learning model loses accuracy for seismocardiogram systolic detection under real-world domain shifts.
Why the study?
Existing deep learning approaches for seismocardiographic systolic complex detection are limited to controlled settings and single datasets, leaving performance in dynamic real-world settings unclear.
Deep learning models for seismocardiogram systolic detection face significant performance drops in real-world dynamic settings compared to controlled environments, highlighting the need for multi-channel approaches and robust domain adaptation.
Answers are grounded in this paper and cite their sources.
SCG systolic detection requires caution before real-world deployment; leaves open optimal domain-adaptation strategies for future models.
The seismocardiographic signal represents a promising technique for continuous monitoring of cardiac electromechanical activity. The systolic complex is known to be the most informative part of the seismocardiogram and it requires accurate detection to perform further analysis. State-of-the-art solutions based on Deep Learning (DL) have been proven to be effective for systolic complex detection, but existing approaches limit their experimental analysis to controlled settings and consider a single dataset at a time. In our work, an exhaustive experimental analysis was conducted to specifically investigate the problem of SCG systolic detection in the wild, departing from the unrealistic assumptions of existing studies. Specifically, a DL model based on a U-Net was utilized to quantitatively assess the impact of domain shift in different scenarios, and to evaluate the challenges related to the SCG systolic detection in a dynamic real-world setting. For this purpose, a novel experimental framework was designed by combining multiple datasets in different ways. Our experimental framework enabled to perform a two-fold domain shift experimental analysis involving (i) cross-dataset, i.e. different acquisition setting, and (ii) static-dynamic evaluation analysis, considering signals collected during daily-life activities. Our results demonstrated significant differences between tests conducted in a controlled and a real-world environment, with the latter being considerably more challenging. Both cross-dataset and static-dynamic domain shifts resulted in worsening of the detection performance, which could be only partially overcome by traditional model adaptation strategies, such as fine-tuning or personalization. Finally, the benefits of a multi-channel approach in real-world scenarios were demonstrated.
No takes yet. Share an insight, caveat, or question.
Craighero et al. (2025) studied Cardiac electromechanical activity monitoring. Deep Learning model based on a U-Net was evaluated on SCG systolic detection performance. A U-Net deep learning model for seismocardiogram systolic detection showed worsened performance under cross-dataset and static-dynamic domain shifts in real-world environments.
Synapse has enriched 10 related papers. Consider them for comparative context: