Back to Evidence Hub
Case Study S029
2024 Release

Craighero 2024: Cross-dataset SCG Analysis

Craighero et al.
Access Paper

Quick Conclusion: S029 is a critical piece for OpenSCG’s technical strategy. It addresses the 'reality gap'—the fact that models trained on clean lab data often fail in the field. By validating personalization and multi-sensor fusion, it provides a direct scientific foundation for OpenSCG’s 'U-Net v3' and adaptive processing pipeline.


📊 Key Accuracy Metrics

MetricResult
F1-score (Controlled)0.92 to 0.94
F1-score (Real-world z-axis)0.88
F1-score (Real-world personalized)0.93 to 0.95
ModelU-Net for binary semantic segmentation


🔍 Study Analysis

Objective & Population

Deep Learning / Cross-dataset Experimental Analysis. Cohort: Healthy subjects (CEBS, MEC) and subjects in daily life (BioPoli) (N=72).

What it Supports

The study supports the use of multi-channel (accelerometer + gyroscope) deep learning to overcome the challenges of 'domain shift' in real-world SCG monitoring. It proves that personalization (fine-tuning a model on a small amount of a user's own data) significantly boosts accuracy to lab-like levels (~95%).

What it Does Not Support

The study does not support the use of 'out-of-the-box' lab-trained models for reliable real-world monitoring without some form of adaptation or multi-sensor integration.


🛠 Technical Context

Featured Illustration

Fig. 1. AO fiducial points and systolic complexes in a clean portion of SCG signal. Note that the bounding boxes are centered in the AO points.

Fig. 1. AO fiducial points and systolic complexes in a clean portion of SCG signal. Note that the bounding boxes are centered in the AO points.

Study Snapshot

Metadata Summary

Target Population

Healthy subjects (CEBS, MEC) and subjects in daily life (BioPoli)

N

Sample Size

72 Subjects

Validated Metric

0.92 to 0.94

Critical Appraisal
supporting

Demonstrated the necessity of personalization and multi-channel data for robust real-world SCG segmentation.