Prehospital and Disaster Medicine最新文献

Objective: The aim of this study was to summarize the literature on the applications of machine learning (ML) and their performance in Emergency Medical Services (EMS).

Methods: Four relevant electronic databases were searched (from inception through January 2024) for all original studies that employed EMS-guided ML algorithms to enhance the clinical and operational performance of EMS. Two reviewers screened the retrieved studies and extracted relevant data from the included studies. The characteristics of included studies, employed ML algorithms, and their performance were quantitively described across primary domains and subdomains.

Results: This review included a total of 164 studies published from 2005 through 2024. Of those, 125 were clinical domain focused and 39 were operational. The characteristics of ML algorithms such as sample size, number and type of input features, and performance varied between and within domains and subdomains of applications. Clinical applications of ML algorithms involved triage or diagnosis classification (n = 62), treatment prediction (n = 12), or clinical outcome prediction (n = 50), mainly for out-of-hospital cardiac arrest/OHCA (n = 62), cardiovascular diseases/CVDs (n = 19), and trauma (n = 24). The performance of these ML algorithms varied, with a median area under the receiver operating characteristic curve (AUC) of 85.6%, accuracy of 88.1%, sensitivity of 86.05%, and specificity of 86.5%. Within the operational studies, the operational task of most ML algorithms was ambulance allocation (n = 21), followed by ambulance detection (n = 5), ambulance deployment (n = 5), route optimization (n = 5), and quality assurance (n = 3). The performance of all operational ML algorithms varied and had a median AUC of 96.1%, accuracy of 90.0%, sensitivity of 94.4%, and specificity of 87.7%. Generally, neural network and ensemble algorithms, to some degree, out-performed other ML algorithms.

Conclusion: Triaging and managing different prehospital medical conditions and augmenting ambulance performance can be improved by ML algorithms. Future reports should focus on a specific clinical condition or operational task to improve the precision of the performance metrics of ML models.

Introduction: Mass-casualty incidents (MCIs) place extraordinary demands on prehospital medical response. However, there remains limited evidence on best practices in managing MCIs, and therefore, there is a need to systematically synthetize experiences from them to build further evidence.

Study objective: This study aimed to analyze common challenges in prehospital MCI management.

Methods: Seventeen case studies or reports describing 15 MCIs (ie, terrorist attacks, chemical incidents, traffic accidents, weather-related incidents, and fires) were subject to a systematic integrative review.

Results: Common challenges in prehospital MCI management include victim and responder safety- and security-related issues; the need to develop and communicate situational awareness; to develop and apply a prehospital response plan; the ability to deliver care under severe circumstances; and the need for an extended prehospital medical response management strategy.

Conclusion: Resilient prehospital MCI response demands both a clear strategy and improvisation and should be integrated into the overall medical response strategy. Responders must understand the main concepts of prehospital MCI management, have a situational awareness that foresees the event's medical consequences, and have the experience required to interpret the situation. Emergency Medical Services (EMS) personnel and medical incident commanders require specific training and mental preparation to be able to provide care under severe security threats, to improvise beyond routines and guidelines, and to provide care in ways different from their everyday work.

This article discusses changes to the Prehospital and Disaster Medicine (PDM) mission statement which will take effect as of January 1, 2025. The new mission statement focuses on innovative, high-impact, evidence-based research.

In this editorial, upcoming changes to the mission statement, available article types, and instructions for authors are highlighted. These changes are expected to start on January 1, 2025.

Background: This study assesses the operational challenges and clinical outcomes encountered by a university-based Emergency Medical Team (EMT) during the medical search and rescue (mSAR) response to the February 2023 earthquakes in Kahramanmaraş, Turkey.

Methods: In this observational study, data were retrospectively collected from 42 individuals who received mSAR services post-earthquake. The challenges were categorized as environmental, logistical, or medical, with detailed documentation of rescue times, patient demographics, injury types, and medical interventions.

Results: In this mSAR study, 42 patients from 30 operations were analyzed and divided into environmental (26.2%), logistical (52.4%), and medical (21.4%) challenge groups. Median rescue times were 29 (IQR 28-30), 36.5 (IQR 33.75-77.75), and 30.5 (IQR 29.5-35.5) hours for each group, respectively (P = .002). Age distribution did not significantly differ across groups (P = .067). Hypothermia affected 18.2%, 45.5%, and 66.7% in the respective groups. Extremity injuries were most common in the medical group (88.9%). Intravenous access was highest in the medical group (88.9%), while splinting was more frequent in the medical (55.6%) and logistical (18.2%) groups. Hypothermia was most prevalent in the medical group (66.7%), followed by the logistical group (45.5%). Ambulance transport post-rescue was utilized for a minority in all groups.

Conclusion: The study concludes that logistical challenges, more than environmental or medical challenges, significantly prolong the duration of mSAR operations and exacerbate clinical outcomes like hypothermia, informing future enhancements in disaster response planning and execution.