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.

Background: A victim’s gender is a known factor that influences the willingness of adult bystanders to perform cardiopulmonary resuscitation (CPR) if an out-of-hospital cardiac arrest (OHCA) occurs. This study aims to identify whether gender characteristics of OHCA victims are also relevant to schoolchildren, who are the key target group of CPR trainings worldwide. Methods: A prospective, educative intervention study was performed in schoolchildren (5th–7th grade). Schoolchildren’s willingness to perform CPR was assessed by means of questionnaires before (t0) and after (t1) standardized CPR training. Participants were asked how determined they were to perform CPR in male and female OHCA victims on a 5-point Likert scale (not being determined to being very determined). A data analysis was performed according to the gender characteristics of schoolchildren. Results: Overall, 342 schoolchildren aged 10–15 years were included, and 166 male (MG) and 176 female (FG) schoolchildren served as a comparison group. Before (t0) and after (t1) the intervention, females showed a significantly higher general willingness to perform CPR than males (t0: 97.1% vs. 89.0%; p < 0.003 and t1: 95.7% vs. 98.9%; p = 0.038). The general willingness to perform CPR after training had a stronger increase in males (8.0% vs. 2.3%; p = 0.017). In the case that the OHCA victim was female, male schoolchildren were less willing to perform CPR than females at baseline (MG: n = 101;60.8% vs. FG: n = 147;84.5%; p < 0.001) and after training (MG: n = 97;58.4% vs. FG: n = 138;79.3%; p < 0.001). At t1, CPR willingness for female victims was improved in males (MG: n = 36;21.7% vs. FG: n = 19;10.9%; p = 0.006). Conclusions: The gender characteristics of OHCA victims, as well as schoolchildren themselves, have a relevant impact on the willingness to perform CPR. Training concepts should effectively motivate male schoolchildren to reduce preexisting inhibitions, especially towards female OHCA patients. Trial registration: This study was registered at the German Clinical Trials Register (Registration number: DRKS00017707) on 2 August 2019.

Introduction: Video-assisted cardiopulmonary resuscitation (V-CPR) describes an advanced telephone-assisted CPR (T-CPR), in which emergency medical service (EMS) dispatchers view a live video steam of the resuscitation. Dispatchers ’ general attitudes toward and self-assessment in V-CPR have not been previously investigated. Material and Methods: We conducted this quantitative analysis along with a pilot study on V-CPR. After conducting V-CPR with laypersons in a simulation, EMS dispatchers were given questionnaires with 21 items concerning their personal attitude toward V-CPR and their self-assessment in providing instructions. The actual CPR performance achieved was recorded and compared to the dispatchers’ self-assessments. Results: Dispatchers completed 49 questionnaires, and the data is presented descriptively. Over 80% strongly agreed that V-CPR was helpful in guiding and that their feedback improved CPR quality. Fifty-one percent agreed that video images supported them in making a diagnosis, while 44.9% disagreed. A vast majority (80-90% each) strongly agreed that V-CPR helped them recognize CPR issues such as compression point, compression rate, and deterioration. In contrast, data for improved compression depth and release were weaker. Thirty percent found V-CPR to be more stressful or exhausting than T-CPR. A majority stated they would prefer V-CPR as an addition to T-CPR in the future. There was a huge gap between dispatchers’ own view of CPR effort and measured CPR quality. Conclusion: Dispatchers generally embrace V-CPR and praise the abilities it provides. Our results indicate that the use of V-CPR did not automatically result in an overall improvement in guideline-compliant CPR quality.

In this model of massive gastric aspiration, we compared two different laryngoscopes (VieScope and Macintosh) in a randomized, controlled simulation study. The primary endpoint was time to intubation; the secondary endpoints were intubation success (i.e., tracheal tube position) and amount of pulmonary aspiration. Thirty-four anesthetists performed endotracheal intubation using VieScope and Macintosh laryngoscopy in a randomized order on an airway manikin simulating massive regurgitation of gastric fluid. The primary endpoint “time until intubation” could be achieved significantly faster (mean −12.4 s [95% confidence intervals (CI) −19.7 s; −7.3 s]) with Macintosh compared to VieScope (p < 0.001). Concerning “correct tube position”, no statistical difference was found between the devices (p = 1.0). The mean time to first ventilation was −11.1 s [95% CI −18.3 s; −5.3 s] when using Macintosh (p = 0.001). The mean volume of aspirated gastric fluid was lower in the Macintosh group: −90.0 mL [95% CI −235.0 mL; −27.5 mL] (p = 0.011). Data from this simulation study suggest that in a model of massive gastric regurgitation, airway management can be achieved faster and with less gastric aspiration when using a Macintosh laryngoscope compared to a VieScope laryngoscope.