AR-CPR 2.0: Validation of the Accuracy and Precision of a Wearable Coaching System for Improving Chest Compression...

Area of Science:

• Medical Technology
• Pediatric Emergency Medicine
• Cardiopulmonary Resuscitation

Background:

• Pediatric cardiopulmonary resuscitation (CPR) quality is often suboptimal, with low adherence to recommended compression rates and depths.
• Existing feedback systems may lack real-time, in-view coaching capabilities essential for immediate performance correction.

Purpose of the Study:

• To validate the accuracy and precision of the Augmented Reality Cardiopulmonary Resuscitation (AR-CPR) system.
• To assess AR-CPR's ability to measure chest compression rate and depth within clinically relevant ranges.

Main Methods:

• AR-CPR system tested using a programmable oscillation platform (100-140 compressions/min, 4.0-5.5 cm depth) and the Stryker LUCAS3 device.
• Statistical analysis included intraclass correlation coefficients, Bland-Altman analysis, and root-mean-square error.
• Linear regression assessed linearity, and group error modeling estimated clinical thresholds.

Main Results:

• The AR-CPR system demonstrated high accuracy and reliability across 473 simulated and 559 mechanical compressions.
• Minimal mean biases were observed for rate (-0.48, -0.44 CPM) and depth (+0.39, +0.59 cm).
• Excellent intraclass correlation coefficients (0.997 for rate, 0.944 for depth) and strong linear agreement (R² values > 0.90) were achieved.

Conclusions:

• AR-CPR reliably measures chest compression rate and depth with high accuracy and precision.
• The system's performance was validated across variable and fixed testing conditions.
• AR-CPR's features support its potential to enhance pediatric resuscitation training and clinical performance.