Emergency Medicine Specialists Research Articles

Custom GPTs Enhancing Performance and Evidence Compared with GPT-3.5, GPT-4, and GPT-4o? A Study on the Emergency Medicine Specialist Examination.

Given the widespread application of ChatGPT, we aim to evaluate its proficiency in the emergency medicine specialty written examination. Additionally, we compare the performance of GPT-3.5, GPT-4, GPTs, and GPT-4o. The research seeks to ascertain whether custom GPTs possess the essential capabilities and access to knowledge bases necessary for providing accurate information, and to explore the effectiveness and potential of personalized knowledge bases in supporting the education of medical residents. We evaluated the performance of ChatGPT-3.5, GPT-4, custom GPTs, and GPT-4o on the Emergency Medicine Specialist Examination in Taiwan. Two hundred single-choice exam questions were provided to these AI models, and their responses were recorded. Correct rates were compared among the four models, and the McNemar test was applied to paired model data to determine if there were significant changes in performance. Out of 200 questions, GPT-3.5, GPT-4, custom GPTs, and GPT-4o correctly answered 77, 105, 119, and 138 questions, respectively. GPT-4o demonstrated the highest performance, significantly better than GPT-4, which, in turn, outperformed GPT-3.5, while custom GPTs exhibited superior performance compared to GPT-4 but inferior performance compared to GPT-4o, with all p < 0.05. In the emergency medicine specialty written exam, our findings highlight the value and potential of large language models (LLMs), and highlight their strengths and limitations, especially in question types and image-inclusion capabilities. Not only do GPT-4o and custom GPTs facilitate exam preparation, but they also elevate the evidence level in responses and source accuracy, demonstrating significant potential to transform educational frameworks and clinical practices in medicine.

Undergraduate acute care clinical competencies for managing acute care cases in adult patients within a South African in-hospital environment: A modified Delphi Study

IntroductionWith the increase of global population, there has been an increased demand for acute care services both locally and globally. In the absence of an acute care competency-based curriculum in South Africa, this study sought to identify the core competencies required by undergraduate medical students to safely manage adult patients within an acute care setting in a South African hospital environment. MethodologyThe modified Delphi study comprised of three rounds. The traditional Delphi method, which uses the same participants across various rounds, was modified by using different stakeholders across the three rounds. Emergency Medicine (EM) specialist trainees (registrars) generated competencies in round one, which were provided to a multi-disciplinary team with expertise in undergraduate curriculum development in round two, using a 5-point Likert scale for rating their agreement-disagreement. Round three entailed inviting the round one contributors to anonymously comment, via online survey, on the competencies generated in round two. ResultsA total of 34 EM registrars participated during round one and 7 curriculum development experts participated during round two. A total of 120 competencies were identified from the 3-round Delphi study; of these 103 (85.8%) were reached by “Strong Agreement”; 16 (13.3%) reached by “Agreement”; and 1 (0.8%) was undecided. DiscussionThe results of the modified Delphi study contributed to developing a comprehensive list of undergraduate acute care clinical competencies set in a South African context. The value of engaging with medical practitioners at the forefront of delivering acute care in a South African healthcare environment who are exposed on a daily basis to the healthcare needs of society, became evident. The findings of this study highlight and reinforce the importance of contextual relevance during the curriculum development process. ConclusionThe modified Delphi method, based on three iterative rounds and feedback from experts, was effective in reaching consensus on the competencies required by undergraduate medical students to manage acute care adult patients safely within a South African hospital environment.

A trauma expert consensus: Capabilities are required early to improve survivability from traumatic injury.

Mortality reviews examine US military fatalities resulting from traumatic injuries during combat operations. These reviews are essential to the evolution of the military trauma system to improve individual, unit, and system-level trauma care delivery and inform trauma system protocols and guidelines. This study identifies specific prehospital and hospital interventions with the potential to provide survival benefits. US Special Operations Command fatalities with battle injuries deemed potentially survivable (2001-2021) were extracted from previous mortality reviews. A military trauma review panel consisting of trauma surgeons, forensic pathologists, and prehospital and emergency medicine specialists conducted a methodical review to identify prehospital, hospital, and resuscitation interventions (e.g., laparotomy, blood transfusion) with the potential to have provided a survival benefit. Of 388 US Special Operations Command battle-injured fatalities, 100 were deemed potentially survivable. Of these (median age, 29 years; all male), 76.0% were injured in Afghanistan, and 75% died prehospital. Gunshot wounds were in 62.0%, followed by blast injury (37%), and blunt force injury (1.0%). Most had a Maximum Abbreviated Injury Scale severity classified as 4 (severe) (55.0%) and 5 (critical) (41.0%). The panel recommended 433 interventions (prehospital, 188; hospital, 315). The most recommended prehospital intervention was blood transfusion (95%), followed by finger/tube thoracostomy (47%). The most common hospital recommendations were thoracotomy and definitive vascular repair. Whole blood transfusion was assessed for each fatality: 74% would have required ≥10 U of blood, 20% would have required 5 to 10 U, 1% would have required 1 to 4 U, and 5% would not have required blood products to impact survival. Five may have benefited from a prehospital laparotomy. This study systematically identified capabilities needed to provide a survival benefit and examined interventions needed to inform trauma system efforts along the continuum of care. The determination was that blood transfusion and massive transfusion shortly after traumatic injury would impact survival the most. Expert Opinion; Level V.

The accuracy of Gemini, GPT-4, and GPT-4o in ECG analysis: A comparison with cardiologists and emergency medicine specialists

IntroductionGPT-4, GPT-4o and Gemini advanced, which are among the well-known large language models (LLMs), have the capability to recognize and interpret visual data. When the literature is examined, there are a very limited number of studies examining the ECG performance of GPT-4. However, there is no study in the literature examining the success of Gemini and GPT-4o in ECG evaluation. The aim of our study is to evaluate the performance of GPT-4, GPT-4o, and Gemini in ECG evaluation, assess their usability in the medical field, and compare their accuracy rates in ECG interpretation with those of cardiologists and emergency medicine specialists. MethodsThe study was conducted from May 14, 2024, to June 3, 2024. The book “150 ECG Cases” served as a reference, containing two sections: daily routine ECGs and more challenging ECGs. For this study, two emergency medicine specialists selected 20 ECG cases from each section, totaling 40 cases. In the next stage, the questions were evaluated by emergency medicine specialists and cardiologists. In the subsequent phase, a diagnostic question was entered daily into GPT-4, GPT-4o, and Gemini Advanced on separate chat interfaces. In the final phase, the responses provided by cardiologists, emergency medicine specialists, GPT-4, GPT-4o, and Gemini Advanced were statistically evaluated across three categories: routine daily ECGs, more challenging ECGs, and the total number of ECGs. ResultsCardiologists outperformed GPT-4, GPT-4o, and Gemini Advanced in all three groups. Emergency medicine specialists performed better than GPT-4o in routine daily ECG questions and total ECG questions (p = 0.003 and p = 0.042, respectively). When comparing GPT-4o with Gemini Advanced and GPT-4, GPT-4o performed better in total ECG questions (p = 0.027 and p < 0.001, respectively). In routine daily ECG questions, GPT-4o also outperformed Gemini Advanced (p = 0.004). Weak agreement was observed in the responses given by GPT-4 (p < 0.001, Fleiss Kappa = 0.265) and Gemini Advanced (p < 0.001, Fleiss Kappa = 0.347), while moderate agreement was observed in the responses given by GPT-4o (p < 0.001, Fleiss Kappa = 0.514). ConclusionWhile GPT-4o shows promise, especially in more challenging ECG questions, and may have potential as an assistant for ECG evaluation, its performance in routine and overall assessments still lags behind human specialists. The limited accuracy and consistency of GPT-4 and Gemini suggest that their current use in clinical ECG interpretation is risky.

Evaluation of YouTube Videos on Defibrillation Applications in Cardiopulmonary Resuscitation: A Comprehensive Analysis.

In the realm of healthcare, particularly after the COVID-19 pandemic, there is a rising trend of sharing videos on YouTube. The increased popularity of these videos among Internet users can be attributed to the captivating nature of visual and auditory data compared to written information. This study aims to assess the content, accuracy, reliability, and quality of YouTube videos focusing on defibrillation applications-a critical component of cardiopulmonary resuscitation (CPR). On October 17, 2022, a video search was conducted using the keyword "defibrillation" on the YouTube platform, sorted in order of interest. Various parameters, including views, view rate, duration, comments, total likes and dislikes, target population, JAMA, DISCERN, and GQS scores, were recorded. In addition, content information was evaluated by Emergency Medicine specialists. The average video duration was 263.95 seconds, with an average of 90,574.6 views, 587.4 likes, and 19.1 comments. The mean DISCERN score was 35.9 (poor), modified DISCERN score was 1.7, GQS score was 2.7, and JAMA score was 2. The mean score regarding the scope and detail of information in the videos was calculated as 6.1. Deficiencies in the accuracy and reliability of Internet information were observed, mirroring the findings in our study. Supervision in this regard was often found to be inadequate. We advocate for the evaluation of video appropriateness before sharing on the Internet. We believe that platforms ensuring easy access to accurate information about crucial interventions such as CPR will significantly contribute to improving health literacy.

Exploration of the Challenges of COVID-19 from the Perspective of Emergency Medicine Specialists.

Emergency physicians are at the forefront of the medical system in the face of the COVID-19 crisis. Identifying the challenges, along with the strategies and effective measures implemented by them in the face of the COVID-19 crisis, can be a roadmap for future crisis management planning. This study aims to explain the challenges faced by emergency physicians regarding COVID-19. This study is a qualitative content analysis. Data were collected using individual and semistructured interviews. Twenty-seven emergency medical specialists in Fars University of Medical Sciences, Iran, participated in the study by purposive sampling method and were interviewed using semistructured interviews. Participants' experience of COVID-19 led to the extraction of four main themes, including structural factors, threats to the health of the medical team, fluctuations of extremism and wastage in the face of COVID-19, and the country's policymaking hierarchy. Emergency physicians face challenges such as structural factors, health threats, extreme fluctuations, and national policymaking. To avoid surprises and threats, they must predict acute scenarios, provide necessary equipment, address skilled manpower shortages, and adopt appropriate management policies. This includes culture-building, cross-sector coordination, planning, and efficient management to prevent virus spread.

Comparative analysis of ChatGPT, Gemini and emergency medicine specialist in ESI triage assessment

IntroductionThe term Artificial Intelligence (AI) was first coined in the 1960s and has made significant progress up to the present day. During this period, numerous AI applications have been developed. GPT-4 and Gemini are two of the best-known of these AI models. As a triage system The Emergency Severity Index (ESI) is currently one of the most commonly used for effective patient triage in the emergency department. The aim of this study is to evaluate the performance of GPT-4, Gemini, and emergency medicine specialists in ESI triage against each other; furthermore, it aims to contribute to the literature on the usability of these AI programs in emergency department triage. MethodsOur study was conducted between February 1, 2024, and February 29, 2024, among emergency medicine specialists in Turkey, as well as with GPT-4 and Gemini. Ten emergency medicine specialists were included in our study but as a limitation the emergency medicine specialists participating in the study do not frequently use the ESI triage model in daily practice. In the first phase of our study, 100 case examples related to adult or trauma patients were extracted from the sample and training cases found in the ESI Implementation Handbook. In the second phase of our study, the provided responses were categorized into three groups: correct triage, over-triage, and under-triage. In the third phase of our study, the questions were categorized according to the correct triage responses. ResultsIn the results of our study, a statistically significant difference was found between the three groups in terms of correct triage, over-triage, and under-triage (p < 0.001). GPT-4 was found to have the highest correct triage rate with an average of 70.60 (±3.74), while Gemini had the highest over-triage rate with an average of 35.2 (±2.93) (p < 0.001). The highest under-triage rate was observed in emergency medicine specialists (32.90 (±11.83)). In the ESI 1–2 class, Gemini had a correct triage rate of 87.77%, GPT-4 had 85.11%, and emergency medicine specialists had 49.33%. ConclusionIn conclusion, our study shows that both GPT-4 and Gemini can accurately triage critical and urgent patients in ESI 1&2 groups at a high rate. Furthermore, GPT-4 has been more successful in ESI triage for all patients. These results suggest that GPT-4 and Gemini could assist in accurate ESI triage of patients in emergency departments.

Impact of the geriatric emergency medicine specialist intervention on final emergency department disposition.

The Geriatric Emergency Medicine Specialist (GEMS) pilot program is an innovative approach that utilizes geriatric-trained advanced practice providers to facilitate geriatric assessments and care planning for older adults in the emergency department (ED). The objective of this study was to explore the effect of GEMS on the use of observation status and final ED disposition. This was a retrospective study under a target trial emulation framework. Geriatric patients (65+ years old) who presented to two ED sites within a large regional healthcare system between December 2020 and December 2022 were included. The primary outcome was final ED disposition (discharge, hospital inpatient admission, or hospital observation admission). Secondary outcomes included ED observation and ED length of stay. Non-GEMS patients were propensity score matched 5:1 to GEMS patients. Doubly robust regression was used to estimate the odds ratios and 95% confidence intervals of inpatient admission, discharge, hospital observation admission, ED observation admission, and estimate the mean ED length of stay. A total of 427 of 43,064 total patients (1.0%) received a GEMS intervention during the study period. Our analysis included 2,302 geriatric ED patients (410 GEMS, 1,892 non-GEMS) after propensity score matching. Hospital admission rates were 34.1% for GEMS compared to 56.4% for conventional treatment. GEMS patients had decreased odds of inpatient admission (OR: 0.41, 95 CI: 0.34-0.51, p < 0.001), increased odds of discharge (OR: 1.19 95 CI: 1.00-1.42, p = 0.047), hospital observation admission (OR: 2.97, 95 CI: 2.35-3.75, p < 0.001), ED observation admission (OR: 4.84 95 CI: 3.67-6.38, p < 0.001), and had a longer average ED length of stay (170 min, 95 CI: 84.6-256, p < 0.001) compared to non-GEMS patients. Patients seen by GEMS during their ED visit were associated with higher rates of hospital discharge and lower rates of hospital admissions.

Comparison of emergency medicine specialist, cardiologist, and chat-GPT in electrocardiography assessment

IntroductionChatGPT, developed by OpenAI, represents the cutting-edge in its field with its latest model, GPT-4. Extensive research is currently being conducted in various domains, including cardiovascular diseases, using ChatGPT. Nevertheless, there is a lack of studies addressing the proficiency of GPT-4 in diagnosing conditions based on Electrocardiography (ECG) data. The goal of this study is to evaluate the diagnostic accuracy of GPT-4 when provided with ECG data, and to compare its performance with that of emergency medicine specialists and cardiologists. MethodsThis study has received approval from the Clinical Research Ethics Committee of Hitit University Medical Faculty on August 21, 2023 (decision no: 2023–91). Drawing on cases from the “150 ECG Cases” book, a total of 40 ECG cases were crafted into multiple-choice questions (comprising 20 everyday and 20 more challenging ECG questions). The participant pool included 12 emergency medicine specialists and 12 cardiology specialists. GPT-4 was administered the questions in a total of 12 separate sessions. The responses from the cardiology physicians, emergency medicine physicians, and GPT-4 were evaluated separately for each of the three groups. ResultsIn the everyday ECG questions, GPT-4 demonstrated superior performance compared to both the emergency medicine specialists and the cardiology specialists (p < 0.001, p = 0.001). In the more challenging ECG questions, while Chat-GPT outperformed the emergency medicine specialists (p < 0.001), no significant statistical difference was found between Chat-GPT and the cardiology specialists (p = 0.190). Upon examining the accuracy of the total ECG questions, Chat-GPT was found to be more successful compared to both the Emergency Medicine Specialists and the cardiologists (p < 0.001, p = 0.001). ConclusionOur study has shown that GPT-4 is more successful than emergency medicine specialists in evaluating both everyday and more challenging ECG questions. It performed better compared to cardiologists on everyday questions, but its performance aligned closely with that of the cardiologists as the difficulty of the questions increased.

Virtual urgent care is here to stay: driving toward safe, equitable, and sustainable integration within emergency medicine.

Virtual care in Canada rapidly expanded during the COVID-19 pandemic in a low-rules environment in response to pressing needs for ongoing access to care amid public health restrictions. Emergency medicine specialists now face the challenge of advising on which virtual urgent care services ought to remain as part of comprehensive emergency care. Consideration must be given to safe, quality, and appropriate care as well as issues of equitable access, public demand, and sustainability (financial and otherwise). The aim of this project was to summarize current literature and expert opinion and formulate recommendations on the path forward for virtual care in emergency medicine. We formed a working group of emergency medicine physicians from across Canada working in a variety of practice settings. The virtual care working group conducted a scoping review of the literature and met monthly to discuss themes and develop recommendations. The final recommendations were circulated to stakeholders for input and subsequently presented at the 2023 Canadian Association of Emergency Physicians (CAEP) Academic Symposium for discussion, feedback, and refinement. The working group developed and reached unanimity on nine recommendations addressing the themes of system design, equity and accessibility, quality and patient safety, education and curriculum, financial models, and sustainability of virtual urgent care services in Canada. Virtual urgent care has become an established service in the Canadian health care system. Emergency medicine specialists are uniquely suited to provide leadership and guidance on the optimal delivery of these services to enhance and complement emergency care in Canada.

Assessing the precision of artificial intelligence in ED triage decisions: Insights from a study with ChatGPT

BackgroundThe rise in emergency department presentations globally poses challenges for efficient patient management. To address this, various strategies aim to expedite patient management. Artificial intelligence's (AI) consistent performance and rapid data interpretation extend its healthcare applications, especially in emergencies. The introduction of a robust AI tool like ChatGPT, based on GPT-4 developed by OpenAI, can benefit patients and healthcare professionals by improving the speed and accuracy of resource allocation. This study examines ChatGPT's capability to predict triage outcomes based on local emergency department rules. MethodsThis study is a single-center prospective observational study. The study population consists of all patients who presented to the emergency department with any symptoms and agreed to participate. The study was conducted on three non-consecutive days for a total of 72 h. Patients' chief complaints, vital parameters, medical history and the area to which they were directed by the triage team in the emergency department were recorded. Concurrently, an emergency medicine physician inputted the same data into previously trained GPT-4, according to local rules. According to this data, the triage decisions made by GPT-4 were recorded. In the same process, an emergency medicine specialist determined where the patient should be directed based on the data collected, and this decision was considered the gold standard. Accuracy rates and reliability for directing patients to specific areas by the triage team and GPT-4 were evaluated using Cohen's kappa test. Furthermore, the accuracy of the patient triage process performed by the triage team and GPT-4 was assessed by receiver operating characteristic (ROC) analysis. Statistical analysis considered a value of p < 0.05 as significant. ResultsThe study was carried out on 758 patients. Among the participants, 416 (54.9%) were male and 342 (45.1%) were female. Evaluating the primary endpoints of our study - the agreement between the decisions of the triage team, GPT-4 decisions in emergency department triage, and the gold standard - we observed almost perfect agreement both between the triage team and the gold standard and between GPT-4 and the gold standard (Cohen's Kappa 0.893 and 0.899, respectively; p < 0.001 for each). ConclusionOur findings suggest GPT-4 possess outstanding predictive skills in triaging patients in an emergency setting. GPT-4 can serve as an effective tool to support the triage process.

ACİL SERVİS PERSONELLERİNİN KİMYASAL, BİYOLOJİK, RADYASYON VE NÜKLEER ACİLLERE HAZIRLIK DÜZEYLERİNİN DEĞERLENDİRİLMESİ

Purpose: The aim of this study is to determine the chemical, biological, radiation, and nuclear (CBRN) emergency preparedness levels of emergency department (ED) personnel. Materials and Methods: This cross-sectional descriptive survey study was conducted with 49 emergency department personnel (emergency medicine specialists, emergency medicine research assistants, nurses, and nursing staffs) working in the ED of a university hospital through face-to-face. The questionnaire was created by the researchers and consisted of 5 demographic and 30 CBRN preparation information, 12 questions questioning the previous practice and educational status of CBRN subjects. The preparedness level of the participants was determined by evaluating the CBRN preparedness level responses. Results: The Cronbach's Alpha reliability index obtained for the CBRN scale was obtained as α=0,856 for the whole scale and this value shows that the reliability of the whole scale is at a good level. The mean preparedness level score of the ED personnel is 59,7 (min-max:24-81). The mean CBRN preparedness level score of emergency medicine specialists (38) was found to be lower than the other groups. The number of those who received training on CBRN situations and medical management of cases during their professional training (bachelor-master- doctorate education) is 18 (36,7%). Most of the participants didn’t participate in any CBRN exercise during their professional life (n=43, 87,8%). Conclusion: ED personnel's preparations for CBRN emergencies are insufficient. Their participation in training and exercises for the medical management of CBRN cases is low. Our study can be used as a tool to determine the CBRN preparations of ED personnel.

Challenges and Barriers Affecting the Quality of Triage in Emergency Departments: A Qualitative Study

Background: Correct and fast triage is the key to successful performance in emergency departments. Various factors can affect the quality of triage; therefore, the present study was conducted to identify and explore the existing challenges in triage units in emergency departments. Materials and Methods: The present study was a qualitative exploratory work conducted via the content analysis approach. Data were collected using in-depth, semi-structured interviews, and focus group interviews. Accordingly, 22 in-depth, semi-structured interviews were conducted in with 18 triage nurses and four emergency medicine specialists on a face-to-face basis. Results: The challenges related to triage nurses fall into two subcategories; lack of clinical competency and psychological capabilities. The challenges related to emergency management consist of challenges in human resources management, structural, and performance. Conclusion: The challenges existing in triage units are influenced by factors related to triage nurses and emergency management. Emergency administrators can improve the effectiveness and quality of triaging patients by empowering triage nurses and removing structural problems in triage units.[GMJ.2019;8:e1619]Â

COMPARISON OF PERFORMANCES OF OPEN ACCESS NATURAL LANGUAGE PROCESSING BASED CHATBOT APPLICATIONS IN TRIAGE DECISIONS

Objective: Being publicly available, easy to use, and continuously evolving, next-generation chatbots have the potential to be used in triage, one of the most critical functions of an Emergency Department. The aim of this study was to assess the performance of Generative Pre-trained Transformer 4 (GPT-4), Bard and Claude during decision-making for Emergency Department triage.&#x0D; Material and Methods: This was a preliminary cross-sectional study conducted with 50 case scenarios. Emergency Medicine specialists determined the reference Emergency Severity Index triage category of each scenario. Subsequently, each case scenario was queried using three chatbots. Inconsistent classifications between the chatbots and references were defined as over-triage (false positive) or under-triage (false negative). The primary and secondary outcomes were the predictive performance of chatbots and the difference between them in predicting high acuity triage.&#x0D; Results: F1 Scores for GPT-4, Bard, and Claude for predicting Emergency Severity Index 1 and 2 were 0.899, 0.791, and 0.865 respectively. The ROC Curve of GPT-4 for high acuity predictions showed an area under the curve (AUC) of 0.911 (95% CI: 0,814-1; p

Developing an Emergency Medicine assessment tool for medical interns within the South African context – A Modified Delphi Study

IntroductionEmergency Medicine is a relatively new specialty in South Africa. Limited data is available regarding junior doctors’ competence in managing emergencies, however previous surveys have identified limited teaching and supervision of junior doctors in Emergency Medicine. Currently there is no formal standardised assessment tool to assess an intern's Emergency Medicine competence. The aim of the study was to, through expert opinion and consensus, develop an Emergency Medicine assessment tool to identify a level of appropriate Emergency Medicine knowledge at the end of internship. MethodsThe Modified Delphi Methodology was used to create an assessment tool via interaction with a panel of experts and took place over 4 rounds via an online survey platform. The initial round identified the high-priority topics within each intern domain. A questionnaire was created based on these topics and was presented to the panel for consensus during the following round/s. Rounds continued until each question met consensus of 75 %. ResultsA total of 35 panellists consented to participate, representing 6 provinces. The majority were Emergency Medicine specialists. High-priority topics included acute respiratory distress, polytrauma, dehydration and shock in children, airway management, and the agitated patient. A 40-question, multiple choice questionnaire was created with all questions reaching consensus. ConclusionThis study highlighted the core high-priority Emergency Medicine topics that interns should be exposed to during their internship and created a questionnaire aimed at evaluating them. The study findings provide a novel contribution to identifying gaps in Emergency Medicine knowledge during intern training, allowing for potential interventions to be implemented to improve intern EM training. The addition of a clinical skills component and increasing the question database is suggested to further develop this tool. Larger iterative studies involving the HPCSA, and health education experts provide avenues for future research.

Deep learning-based natural language processing for detecting medical symptoms and histories in emergency patient triage

ObjectiveThe manual recording of electronic health records (EHRs) by clinicians in the emergency department (ED) is time-consuming and challenging. In light of recent advancements in large language models (LLMs) such as GPT and BERT, this study aimed to design and validate LLMs for automatic clinical diagnoses. The models were designed to identify 12 medical symptoms and 2 patient histories from simulated clinician–patient conversations within 6 primary symptom scenarios in emergency triage rooms. Materials and methodWe developed classification models by fine-tuning BERT, a transformer-based pre-trained model. We subsequently analyzed these models using eXplainable artificial intelligence (XAI) and the Shapley additive explanation (SHAP) method. A Turing test was conducted to ascertain the reliability of the XAI results by comparing them to the outcomes of tasks performed and explained by medical workers. An emergency medicine specialist assessed the results of both XAI and the medical workers. ResultsWe fine-tuned four pre-trained LLMs and compared their classification performance. The KLUE-RoBERTa-based model demonstrated the highest performance (F1-score: 0.965, AUROC: 0.893) on human-transcribed script data. The XAI results using SHAP showed an average Jaccard similarity of 0.722 when compared with explanations of medical workers for 15 samples. The Turing test results revealed a small 6% gap, with XAI and medical workers receiving the mean scores of 3.327 and 3.52, respectively. ConclusionThis paper highlights the potential of LLMs for automatic EHR recording in Korean EDs. The KLUE-RoBERTa-based model demonstrated superior classification performance. Furthermore, XAI using SHAP provided reliable explanations for model outputs. The reliability of these explanations was confirmed by a Turing test.

Trauma System in Albania. A challenge that Requires long-term and Sustainable Solutions.

&#x0D; &#x0D; &#x0D; &#x0D; &#x0D; &#x0D; &#x0D; &#x0D; &#x0D; &#x0D; &#x0D; &#x0D; Introduction Developing an effective trauma care system is an ongoing challenge in Albania, as it is in many countries. Trauma remains a significant cause of morbidity and mortality, particularly among the younger population in Albania. While the need for a structured trauma system has been recognized, several challenges need to be addressed.&#x0D; Lack of a Formalized Trauma System: Albania lacks a formalized and well-structured trauma system that can efficiently manage trauma cases from the scene of the injury to rehabilitation. The absence of such a system can lead to delays in care and suboptimal outcomes.&#x0D; Inconsistent Data Collection and Quality Improvement: Uniform data collection, quality improvement programs, and trauma verification processes are not consistently implemented. This results in fragmented and inconsistent trauma care, making it challenging to track and improve outcomes.&#x0D; Shortage of Specialized Trauma Care Personnel: The scarcity of healthcare professionals with specialized training in trauma care, including trauma surgeons and emergency medicine specialists, presents a significant hurdle. Trauma care requires a multidisciplinary approach with expertise in various aspects of care, from initial resuscitation to surgical intervention.&#x0D; Infrastructure and Resource Limitations: Many healthcare facilities, especially in rural areas, lack the necessary infrastructure, equipment, and resources to provide optimal trauma care. This includes deficiencies in trauma centers, emergency departments, and pre-hospital care.&#x0D; Challenges in Transportation and Prehospital Care: Efficient prehospital care and transportation of trauma patients are critical for improving outcomes. In Albania, challenges related to transportation and the availability of trained paramedics can hinder the timely delivery of care.&#x0D; Public Awareness and Injury Prevention: Raising public awareness about injury prevention and safety measures is essential. Efforts to reduce the incidence of trauma, especially road traffic accidents, can have a significant impact on overall trauma rates.&#x0D; Coordination Among Healthcare Facilities: Effective coordination among healthcare facilities, from local clinics to major hospitals, is crucial for seamless patient transfer and continuity of care.&#x0D; Advocacy and Government Support: Advocacy efforts by healthcare professionals and organizations are needed to emphasize the importance of a formalized trauma system. Government support and funding are essential for building and maintaining a trauma care infrastructure.&#x0D; Conclusion: establishing a comprehensive trauma system in Albania is a multifaceted challenge that requires collaboration among healthcare stakeholders, advocacy, resource allocation, and a commitment to improving trauma care from the moment of injury through rehabilitation. This ongoing challenge is critical for reducing trauma-related morbidity and mortality in the country.&#x0D; &#x0D; &#x0D; &#x0D; &#x0D; &#x0D; &#x0D; &#x0D; &#x0D; &#x0D; &#x0D; &#x0D; &#x0D; &#x0D;

Assessing the Awareness of EVTM Practices Among Emergency Medicine Physicians in Turkey

Background: Trauma is the leading cause of death in those aged 1–44 years; nearly half of these fatalities are due to bleeding. As resuscitative endovascular balloon occlusion of the aorta (REBOA) and other endovascular resuscitation and trauma management (EVTM) methods became known in Turkey, they started to arouse interest. The main objective of this study is to reveal the impressions of emergency medicine (EM) doctors about EVTM and REBOA application possibilities, and the secondary objective is to determine the issues that are limiting their spread. Methods: We conducted a 22-question cross-sectional survey via e-mail between 1 January and 1 April 2020. The questions were formulated to be closed-ended, semi-closed-ended, and open-ended. The evaluation questions utilized 3- and 5-point Likert scales and Yes/No questions. EM specialists, residents, consultants, and physicians working as emergency department (ED) directors in Turkey were included. EM specialists working in units other than EDs and specialists from other branches were excluded. Results: Among the 512 people contacted for this study, 132 agreed to participate. The numbers of participants that were aware of REBOA and EVTM were 114 and 99, respectively. Participants thought that femoral vascular access, extracorporeal membrane oxygenation (ECMO), and REBOA were more applicable in EDs (median 4, 4, and 4.5, respectively; interquartile range 1–5). Participants considered lack of knowledge and skills and lack of equipment as barriers to REBOA (median 5 and 5, respectively). Conclusions: To disseminate EVTM practices in Turkey, projects should be conducted primarily to address lack of knowledge, skills, and equipment.

Creation and Establishment of the State Emergency Medical Services and Disaster Medicine Services in Russia (to the 100th Anniversary of the N.V. Sklifosovsky Research Institute for Emergency Medicine)

After the October Revolution of 1917, the creation of the state healthcare and medical education system in the country played a decisive role in the organization of emergency medical services (EMS) in Moscow on the basis of the former Sheremetev Hospital which later became a large multidisciplinary medical institution — N.V. Sklifosovsky Institute of Emergency Medicine (since 1943 — N.V. Sklifosovsky Research Institute for Emergency Medicine), — and the city EMS station as a part of it.In the pre-war period, the working out of the main principles for the EMS provision was critically important for the development of the services. It became possible to solve scientific and methodological problems related to the training of specialists. The Institute grew into a large institution, research in the field of emergency medicine was carried out at the world level. This contributed to the organization of a network of EMS institutions in the country during 1926–1935.The years of the Great Patriotic War of 1941–1945 enriched the practice of providing emergency medical care, including during mass patient admission.In the post-war years (1946–1970s), the Institute became the leading institution on the problems of EMS in the country. Corresponding divisions were created within the Institute, and on its basis — “Emergency Medicine” scientific and practical association, research and organizational structures of the USSR Ministry of Health, the RSFSR Ministry of Health and the USSR Academy of Medical Sciences. Thanks to this, outstanding results were achieved in the EMS organization: the specialty of “emergency medicine physician” was introduced; emergency hospitals were created in a number of the country’s regions; government programs for EMS provision were successfully implemented; а large number of regulatory documents were prepared to facilitate the further EMS development.N.V. Sklifosovsky Research Institute for Emergency Medicine was among the main initiators of the disaster medicine service, which made it possible to fundamentally solve its organizational and technical problems. Thus, a significant contribution was made to the foundation of this service in Moscow and around the country.At the current stage (from 1992 to the present), EMS improvement has been continued, many developments turned out to be relevant for this services in the Russian Federation. In particular, the created structure of the Institute’s admission and intensive care unit remained the flagship among emergency care institutions in the country for about 20 years. The state program “Improving medical care for road accident victims” was successfully implemented. The Institute’s departments are being actively specialized, making it possible to obtain fundamentally new scientific and practical results for widespread implementation.Since 2011, “Scientific achievements in the field of emergency medical care in the Russian Federation” - collections of research works - have been published annually. The information presented in them can be used throughout the country.The experience in treatment for the novel coronavirus infection COVID-19 allowed the Institute to begin a new page in the history of emergency medical services.The recent opening of an emergency inpatient complex at the Institute contributed to optimizing the work of the hospital’s resuscitation and intensive care units and expanding their treatment and diagnostic capabilities.For more than 10 years, the public and consolidating activities of the scientific and practical society of emergency medicine specialists have been effective. Its work primarily concerns the organization and conduct of scientific and practical events, especially congresses of emergency medicine physicians, as well as the publication of Sklifosovsky Journal Emergency Medical Care, which has unifying significance for a large number of Russian specialists in the field of EMS. The decisions made at the congresses and conferences became the basis for expanding the introduction of advanced medical technologies in the Russian regions, as well as for carrying out important structural reforms in EMS institutions.One of the main achievements of the N.V. Sklifosovsky Research Institute for Emergency Medicine is the creation of the state EMS as a separate branch of healthcare in the country. Over the 100 years of the Institute’s activity, the foundations of its theory and practice have been developed, moreover, a contribution of world significance was made to the EMS development, thereby strengthening the scientific foundation for the activities of the Institute for many years to come.

The Effectiveness of Cognitive-Behavioral Therapy Courses in Improving the Emergency Medicine Residents and Interns' Ability to Regulate their Emotions in Threatening or Stressful Events.

Given that the duties of an emergency medicine (EM) specialist are much more complicated than the other health care professionals, inexperience, weakness or inability to make appropriate decisions, and lack of control over their emotions and stress can lead to medical errors. This study aimed at determining the effect of cognitive-behavioral therapy (CBT) of emotion regulation on the EM assistants' and interns' level of satisfaction and cognitive control of anger and stress. In this study, 25 EM residents and interns were trained in the virtual CBT course while 19 ones were not given any training in the control group and Cognitive Emotion Regulation Questionnaire (CERQ) were filled before and after the training intervention. After the training intervention, the dimensions of catastrophizing and other blame in the experimental group with the means of 3.84 ± 1.40 and 3.16 ± 0.94 respectively were significantly lower than these dimensions in the control group with the means of 5.68 ± 1.76 and 4.73 ± 1.15, respectively (P value < 0.05). Moreover, the refocus on planning in the experimental group with the means of 8.40 ± 1.53 was significantly higher than in the control group with the means of 7.00 ± 2.05 (P value < 0.05). CBT method used in this study may be effective in controlling the emotions of EM interns and residents. CBT may help them to regulate anger and stress and have the ability to control their emotions during or after the experience of threatening or stressful events.