Feasibility of real-time compression frequency and compression depth assessment in CPR using a “machine-learning” artificial intelligence tool

• Published in: Resuscitation plus 2024-12, Vol.20, p.100825, Article 100825
• Main Authors: Ecker, Hannes, Adams, Niels-Benjamin, Schmitz, Michael, Wetsch, Wolfgang A.
• Format: Article
• Language: English
• Subjects: Artificial Intelligence; Body-tracking; Cardiopulmonary resuscitation; CPR; EMS Dispatching; Machine Learning; Pose-tracking; Simulation and Education; T-CPR; Telephone assisted cardiopulmonary resuscitation; V-CPR; Video-assisted cardiopulmonary resuscitation
• ISSN: 2666-5204; 2666-5204
• DOI: 10.1016/j.resplu.2024.100825

Video assisted cardiopulmonary resuscitation (V-CPR) has demonstrated to be efficient in improving CPR quality and patient outcomes, as Emergency Medical Service (EMS) dispatchers can use the video stream of a caller for diagnostic purposes and give instructions in a CPR scenario. However, the new challenges faced by EMS dispatchers during video-guided CPR (V-CPR)—such as analyzing the video stream, providing feedback to the caller, and managing stress—demand innovative solutions. This study explores the feasibility of incorporating an open-source “machine-learning” tool (artificial intelligence – AI), to evaluate the feasibility and accuracy in correctly detecting the actual compression frequency and compression depth in video footage of a simulated CPR. MediaPipe Pose Landmark Detection (Google LLC, Mountain View, CA, USA), an open-source AI software using “machine-learning” models to detect human bodies in images and videos, was programmed to assess compression frequency an depth in nine videos, showing CPR on a resuscitation manikin. Compression frequency and depth were assessed from compression to compression with AI software and were compared to the manikin’s internal software (QCPR, Laerdal, Stavanger, Norway). After testing for Gaussian distribution, means of non-gaussian data were compared using Wilcoxon matched-pairs signed rank test and the Bland Altman method. MediaPipe Pose Landmark Detection successfully identified and tracked the person performing CPR in all nine video sequences. There were high levels of agreement between compression frequencies derived from AI and manikin’s software. However, the precision of compression depth showed major inaccuracies and was overall not accurate. This feasibility study demonstrates the potential of open-source “machine-learning” tools in providing real-time feedback on V-CPR video sequences. In this pilot study, an open-source landmark detection AI software was able to assess CPR compression frequency with high agreement to actual frequency derived from the CPR manikin. For compression depth, its performance was not accurate, suggesting the need for adjustment. Since the software used is currently not intended for medical use, further development is necessary before the technology can be evaluated in real CPR.