A Real-Time Digital Twin Synchronization Framework for Multi-Sensor Cardiopulmonary Resuscitation Measurement

Area of Science:

• Biomedical Engineering
• Digital Health
• Wearable Technology

Background:

• Cardiopulmonary resuscitation (CPR) quality is critical for patient outcomes.
• Real-time feedback systems for CPR training are essential for skill improvement.
• Existing CPR monitoring systems often lack accuracy and robustness.

Purpose of the Study:

• To propose a digital twin-based CPR compression measurement system (DTCMS) architecture.
• To enable real-time monitoring and biomechanical analysis of CPR compressions.
• To enhance CPR training through synchronized physical-virtual interaction.

Main Methods:

• Integration of a load cell, inertial measurement unit (IMU), LabVIEW platform, and Convolutional Neural Network (CNN) module.
• Development of a calibration-aware sensor fusion framework for synchronizing heterogeneous signals.
• Implementation of real-time data acquisition, latency-controlled transmission, and digital twin visualization.

Main Results:

• High accuracy (R² > 0.99) and stable repeatability (CV < 3.5%) in CPR compression measurement.
• Compression depth error maintained within ±1.5 mm.
• Synchronization latency consistently below 0.2 seconds, demonstrating robust dynamic tracking.

Conclusions:

• The proposed DTCMS architecture provides a robust solution for real-time biomechanical monitoring.
• Calibration-aware multi-sensor fusion significantly improves synchronization stability and sensing robustness.
• The digital twin-based system offers enhanced CPR training and interactive feedback.