Quick Conclusion: S045 (FOSTER) is a high-quality 2025 dataset that represents the future of multimodal 'Force-based' monitoring. For OpenSCG, it provides the precise temporal alignment needed to train models that combine vibrations (SCG) with acoustic data (PCG), enabling more robust detection of heart valve events.
📊 Key Accuracy Metrics
| Metric | Result |
|---|---|
| Total Data | 7 minutes per subject @ 10 kHz sampling rate |
| SCG SNR | 83.73 ± 0.53 dB |
| IBI Accuracy (dHF-FCG vs ECG) | R2 > 0.99, Bias 0.0 ms, LoA ~±6 ms |
| Repository | osf.io/3u6yb |
🔍 Study Analysis
Objective & Population
Dataset Description / Technical Validation Study. Cohort: 40 healthy subjects (20 males, 20 females), Age 26.93 ± 7.09 (N=40).
What it Supports
The study supports the integration of multiple mechanical sensing modalities (SCG, FCG, PCG) for a holistic view of heart function. It proves that mechanical sensors can track heart and breathing rates with high precision (unit slopes vs ECG) and provides a unique high-frequency (10 kHz) dataset for developing advanced AI algorithms.
What it Does Not Support
This study does not provide diagnostic evidence for heart failure or other pathologies, as the cohort consisted of young, healthy volunteers.
🛠 Technical Context
- DOI: 10.1038/s41597-025-05694-2
- Authors: A. Parlato et al.
- Confidence Tier: Supporting
