Machine learning-based dispatch of drone-delivered defibrillators for out-of-hospital cardiac arrest.

BACKGROUND: Drone-delivered defibrillators have the potential to significantly reduce response time for out-of-hospital cardiac arrest (OHCA). However, optimal policies for the dispatch of such drones are not yet known. We sought to develop dispatch rules for a network of defibrillator-carrying drones. METHODS: We identified all suspected OHCAs in Peel Region, Ontario, Canada from Jan. 2015 to Dec. 2019. We developed drone dispatch rules based on the difference between a predicted ambulance response time to a calculated drone response time for each OHCA. Ambulance response times were predicted using linear regression and neural network models, while drone response times were calculated using drone specifications from recent pilot studies and the literature. We evaluated the dispatch rules based on response time performance and dispatch decisions, comparing them to two baseline policies of never dispatching and always dispatching drones. RESULTS: A total of 3573 suspected OHCAs were included in the study with median and mean historical ambulance response times of 5.8 and 6.2 min. All machine learning-based dispatch rules significantly reduced the median response time to 3.9 min and mean response time to 4.1-4.2 min (all P < 0.001) and were non-inferior to universally dispatching drones (all P < 0.001) while reducing the number of drone flights by up to 30%. Dispatch rules with more drone flights achieved higher sensitivity but lower specificity and accuracy. CONCLUSION: Machine learning-based dispatch rules for drone-delivered defibrillators can achieve similar response time reductions as universal drone dispatch while substantially reducing the number of trips.

Improving Access to Automated External Defibrillators in Rural and Remote Settings: A Drone Delivery Feasibility Study.

Background Time to treatment is critical for survival from sudden cardiac arrest. Every minute delay in defibrillation results in a 7% to 10% reduction in survival. This is particularly problematic in rural and remote regions, where emergency medical service response is prolonged and automated external defibrillators (AEDs) are often not available. Our primary objective was to examine the feasibility of a novel AED drone delivery method for rural and remote sudden cardiac arrest. A secondary objective was to compare response times between AED drone delivery and ambulance to mock sudden cardiac arrest resuscitations. Methods and Results We conducted 6 simulations in 2 rural communities in southern Ontario, Canada. In the first 2 simulations, the drone and ambulance were dispatched from the same paramedic base. In simulations 3 and 4, the drone and ambulance were dispatched from separate paramedic bases; and in simulations 5 and 6, the drone was dispatched from an optimized location. During each simulation, a "mock" call was placed to 911 and a single AED drone and an ambulance were simultaneously dispatched to a predetermined destination. On scene, trained first responders retrieved the AED from the drone and initiated resuscitative efforts on a mannequin until paramedics arrived. No difficulties were encountered during drone activation by dispatch, ascent, landing, or bystander retrieval of the AED from the drone. During simulations 1 and 2, the distance to the scene was 6.6 km. For simulations 3 and 4, the ambulance response distance increased to 8.8 km while drone remained at 6.6 km; and in simulations 5 and 6, the ambulance response distance was 20 km compared with 9 km for the drone. During each flight, the AED drone arrived on scene before the ambulance, between 1.8 and 8.0 minutes faster. Conclusions This study suggests AED drone delivery is feasible, with the potential for improvements in response time during simulated sudden cardiac arrest scenarios. Further research is required to determine the appropriate system configuration for AED drone delivery in an integrated emergency medical service system as well as optimal strategies to simplify bystander application of a drone-delivered AED.

Observing the stages of bystander intervention in virtual reality simulation.

BACKGROUND: Understanding bystander reactions to an emergency is an important component of effective training. Four stages of bystander intervention (BI) have been previously described: noticing the situation as a problem, interpreting when it is appropriate to intervene, recognizing personal responsibility to intervene, and knowing how to intervene. Using virtual reality (VR) to simulate emergencies such as sudden cardiac arrest (SCA) can be used to study these stages. METHODS: In a secondary analysis of an observational cohort study, we analyzed bystander self-efficacy for stages of BI before and after simulated SCA. Each subject participated in a single-player, immersive, VR SCA scenario. Subjects interacted with simulated bystanders through voice commands ("call 911", "get an AED"). Actions taken in scenario, like performing CPR, were documented. Scenario BI actions were compared based on dichotomized comfort/discomfort. RESULTS: From June 2016 to June 2017, 119 subjects participated. Average age was 37±14 years, 44% were female and 46% reported CPR training within 2 years. During the scenario, 98% "noticed the event" and "interpreted it as a problem", 78% "took responsibility", and 54% "possessed the necessary skills". Self-efficacy increased from pre- to post-scenario: noticing the event increased from 80% to 96%; interpreting as a problem increased from 86% to 97%; taking responsibility increased from 56% to 93%; possessing necessary skills increased from 47% to 63% (P<0.001). CONCLUSION: Self-efficacy to respond to an SCA event increased pre- to post-scenario. Bystanders who reported feeling comfortable "taking responsibility to intervene" during an emergency were more likely to take action during a simulated emergency.

Observing the stages of bystander intervention in virtual reality simulation / 世界急诊医学杂志（英文）

BACKGROUND@#Understanding bystander reactions to an emergency is an important component of effective training. Four stages of bystander intervention (BI) have been previously described: noticing the situation as a problem, interpreting when it is appropriate to intervene, recognizing personal responsibility to intervene, and knowing how to intervene. Using virtual reality (VR) to simulate emergencies such as sudden cardiac arrest (SCA) can be used to study these stages.@*METHODS@#In a secondary analysis of an observational cohort study, we analyzed bystander self-efficacy for stages of BI before and after simulated SCA. Each subject participated in a singleplayer, immersive, VR SCA scenario. Subjects interacted with simulated bystanders through voice commands (“call 911”, “get an AED”). Actions taken in scenario, like performing CPR, were documented. Scenario BI actions were compared based on dichotomized comfort/discomfort.@*RESULTS@#From June 2016 to June 2017, 119 subjects participated. Average age was 37±14 years, 44% were female and 46% reported CPR training within 2 years. During the scenario, 98% “noticed the event” and “interpreted it as a problem”, 78% “took responsibility”, and 54% “possessed the necessary skills”. Self-efficacy increased from pre- to post-scenario: noticing the event increased from 80% to 96%; interpreting as a problem increased from 86% to 97%; taking responsibility increased from 56% to 93%; possessing necessary skills increased from 47% to 63% (P<0.001).@*CONCLUSION@#Self-efficacy to respond to an SCA event increased pre- to post-scenario. Bystanders who reported feeling comfortable “taking responsibility to intervene” during an emergency were more likely to take action during a simulated emergency.

"Please. Don't. Die.": A Grounded Theory Study of Bystander Cardiopulmonary Resuscitation.

BACKGROUND: Bystander cardiopulmonary resuscitation (CPR) is an important determinant of survival from out-of-hospital cardiac arrest (OHCA), yet rates of bystander CPR are highly variable. In an effort to promote bystander CPR, the procedure has been streamlined, and ultrashort teaching modalities have been introduced. CPR has been increasingly reconceptualized as simple, safe, and easy to perform; however, current methods of CPR instruction may not adequately prepare lay rescuers for the various logistical, conceptual, and emotional challenges of resuscitating a victim of cardiac arrest. METHODS AND RESULTS: We adopted a constructivist grounded theory methodology to qualitatively explore bystander CPR and invited lay rescuers who had recently (ie, within 1 week) intervened in an OHCA to participate in semistructured interviews and focus groups. We used constant comparative analysis until theoretical saturation to derive a midrange explanatory theory of bystander CPR. We constructed a 3-stage theoretical model describing a common experiential process for lay rescuer intervention in OHCA: Being called to act is disturbing, causing panic, shock, and disbelief that must ultimately be overcome. Taking action to save the victim is complicated by several misconceptions about cardiac arrest, where victims are mistakenly believed to be choking, and agonal respirations are misinterpreted to mean the victim is alive. Making sense of the experience is challenging, at least in the short term, where lay rescuers have to contend with self-doubt, unanswered questions, and uncomfortable emotional reactions to a traumatic event. CONCLUSIONS: Our study suggests that current CPR training programs may not adequately prepare lay rescuers for the reality of an OHCA and identifies several key knowledge gaps that should be addressed. The long-term psychological consequences of bystander intervention in OHCA remain poorly understood and warrant further study.