BMC Emergency Medicine最新文献

{"title":"Deep learning-based natural language processing for critical care identification in pediatric emergency department.","authors":"Jiyoung Agatha Kim, Sangyeon Cho, Minyoung Hwang, Dongjoon Lee, Jangyeong Jeon, Rhoan Lee, Changhee Lee, Junyeong Kim, Woori Bae","doi":"10.1186/s12873-026-01560-5","DOIUrl":"10.1186/s12873-026-01560-5","url":null,"abstract":"<p><strong>Background: </strong>The initial assessment of pediatric emergency patients is challenging due to diverse clinical presentations and the limited applicability of existing mortality scoring systems that require detailed laboratory results often unavailable at first encounter. Deep learning (DL)-based Natural Language Processing (NLP) offers the ability to extract complex patterns within textual data attained at the first encounter with the physician and can enhance the accuracy and timely prediction of critically ill patients in the Pediatric emergency department (PED). This study identified whether DL-based NLP techniques, which integrate structured data (vital signs) with unstructured data (clinical text written by physicians), can accurately identify patients requiring critical care in PEDs.</p><p><strong>Methods: </strong>Four machine learning (ML) models using term frequency-inverse document frequency-logistic regression, extreme gradient boosting, gradient boosting, and random forest, and two DL-based NLP models based on the Korean Medical Bidirectional Encoder Representations from Transformers (KM-BERT) framework were tested on 87,748 children, including 599 (0.7%) critical cases and 14,095 (16.1%) admission cases in a tertiary hospital, from January 1, 2012, to December 31, 2021.</p><p><strong>Results: </strong>KM-BERT, using a Masked Language Model (MLM), outperformed all ML-based models in predicting critically ill patients, achieving the highest Area Under the Receiver Operating Curve (AUROC) of 0.941 ± 0.015 and an accuracy of 0.952 ± 0.002. It also demonstrated superior performance in predicting hospitalized patients, with an AUROC of 0.879 ± 0.004 and an accuracy of 0.798 ± 0.002.</p><p><strong>Conclusion: </strong>These findings suggest that DL-based NLP approaches, particularly KM-BERT with MLM, may improve the early identification of critically ill and hospitalized pediatric patients in the PED compared with conventional ML-based models. Further prospective, multi-center studies are required to validate these findings and establish their suitability for routine clinical integration.</p>","PeriodicalId":9002,"journal":{"name":"BMC Emergency Medicine","volume":"26 1","pages":""},"PeriodicalIF":3.1,"publicationDate":"2026-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13270580/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148257171","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Brain computed tomography (CT) findings in patients with vertigo and without focal neurological abnormalities in the emergency department of a tertiary center in Saudi Arabia: a retrospective study.","authors":"Saad Mohammed Alshahrani, Faisal Baabbad, Waleed Alharbi, Khalid Bin Aziz, Nawaf Alzahrani, Fahad Bin Aziz, Roaa Amer","doi":"10.1186/s12873-026-01645-1","DOIUrl":"10.1186/s12873-026-01645-1","url":null,"abstract":"<p><strong>Background: </strong>Vertigo is a frequent emergency department (ED) presentation, yet the utility of non-contrast brain computed tomography (CT) in patients without focal neurological deficits remains uncertain. To assess the diagnostic yield of non-contrast brain CT in adult ED patients presenting with isolated vertigo and no focal neurological signs.</p><p><strong>Methods: </strong>A retrospective cross-sectional study was conducted at a tertiary ED in Riyadh, Saudi Arabia, from January 2021 to October 2024. Adult patients presenting with vertigo and a normal neurological exam who underwent non-contrast brain CT were included. Clinical and demographic data were analyzed to determine the prevalence and predictors of positive CT findings.</p><p><strong>Results: </strong>Among 1,206 patients, only 43 (3.6%) had any positive CT findings. Most abnormalities were chronic or non-acute: space-occupying lesions (46.5%) and signs of idiopathic intracranial hypertension (39.5%). Acute pathology-defined as infarction or hemorrhage-was identified in just 6 cases (0.5%), all in patients with at least one cardiovascular risk factor. No acute findings occurred in patients without hypertension, diabetes, or dyslipidemia (n = 446; 0%).</p><p><strong>Conclusion: </strong>The diagnostic yield of non-contrast brain CT in isolated vertigo without focal deficits is extremely low, particularly in patients without vascular comorbidities. Imaging decisions should be guided by risk stratification, reserving CT for patients with cardiovascular risk factors or concerning clinical features. A selective imaging strategy may reduce unnecessary testing and optimize resource use without compromising patient safety.</p>","PeriodicalId":9002,"journal":{"name":"BMC Emergency Medicine","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2026-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13520307/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148257268","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Association between utilisation of pre-hospital emergency services and premature discharge in Emergency Department attendances with mental health triage codes: a retrospective cohort study.","authors":"R Moola, R M Duffy, A Moughty, A M Doherty","doi":"10.1186/s12873-026-01638-0","DOIUrl":"10.1186/s12873-026-01638-0","url":null,"abstract":"<p><strong>Background: </strong>People attending the Emergency Department (ED) with mental health conditions are a vulnerable group who may struggle to engage with scheduled care. Existing research suggests this cohort are more likely to leave before treatment is complete. This study aimed to examine the utilisation rates of pre-hospital emergency services in transferring people with mental health triage codes to the ED, establish rates on incomplete care, and examine any associations between mode of arrival and self-discharge prior to completion of care.</p><p><strong>Methods: </strong>This study utilised retrospective analysis of attendances at an inner-city ED on individuals presenting with a mental health triage code: mental illness; behaving strangely; overdose & poisoning; and self-harm. SPSS was used to perform descriptive, bivariate, and multivariate analyses of patient characteristics and the associations between mode of arrival and self-discharge from 2008 to 2022.</p><p><strong>Results: </strong>During the study period 30,941 patients presented to the ED with mental health triage codes. Of these, 53% (n = 16,390) were brought by ambulance and 3.3% (n = 1,016) by the police service. In total, 28.4% (n = 8,732) left before completion of care. Self-discharge was significantly associated with arrival by ambulance (p < 0.001), less urgent triage categories (p < 0.001), and male gender (p < 0.001). The association between self-discharge and mode of arrival remained significant after controlling for age and gender, triage code and time of arrival (OR = 1.42; p < 0.001).</p><p><strong>Conclusion: </strong>In people attending the ED with mental health problems, self-discharge is more frequent in those brought by ambulance. There is a need for qualitative data to understand the needs of this population and target interventions to avoid premature cessation of treatment.</p><p><strong>Clinical trial number: </strong>Not applicable.</p>","PeriodicalId":9002,"journal":{"name":"BMC Emergency Medicine","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2026-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13520169/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148263184","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The impact of telemedicine on the efficiency and accuracy of emergency department triage: a staff perspective.","authors":"Muhammad Nauman Qureshi, Hamad Aldukhayl, Abdullah Alnatheer, Irteza Neyaz Ahmad, Amjad Alshehry","doi":"10.1186/s12873-026-01580-1","DOIUrl":"10.1186/s12873-026-01580-1","url":null,"abstract":"","PeriodicalId":9002,"journal":{"name":"BMC Emergency Medicine","volume":"26 1","pages":""},"PeriodicalIF":3.1,"publicationDate":"2026-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13270681/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148257234","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Diagnostic accuracy of large language models for emergency department triage: a systematic review and meta-analysis.","authors":"Limei Cui, Mengting Wang, Ye Xu, Wei Wei, Xuehong Zhao","doi":"10.1186/s12873-026-01639-z","DOIUrl":"10.1186/s12873-026-01639-z","url":null,"abstract":"<p><strong>Objective: </strong>Large language models (LLMs) have shown potential in the field of emergency department (ED) triage. However, a comprehensive evaluation of their diagnostic performance and a comparison with triage nurses have not been extensively explored. To systematically evaluate the comparative triage accuracy of LLMs versus triage nurses in ED, assess their performance in identifying patients assigned to the highest-acuity triage category by the reference standard.</p><p><strong>Methods: </strong>A systematic search was conducted in CNKI, Wanfang, VIP, CBM, PubMed, Embase, Web of Science, and Cochrane Library databases from inception to March 2025. Two researchers independently screened and evaluated the quality of the selected studies and conducted meta-analyses using RevMan 5.4 and Stata 16.0.</p><p><strong>Results: </strong>A total of 11 studies were included, involving 3088 real or simulated ED cases. The pooled odds ratio (OR) for LLM triage accuracy was 0.65 (95% CI: 0.32-1.34; I² = 97%). For identifying patients assigned to the highest-acuity triage category by the reference standard, LLMs demonstrated a pooled sensitivity of 61% (95% CI: 48%-73%) and specificity of 97% (95% CI: 88%-99%), with statistically significant differences (p < 0.05). The pooled area under the curve (AUC) was 0.82 (95% CI: 0.78-0.85). These estimates reflect concordance with triage category by the reference standard rather than discrimination of outcome-anchored physiological acuity. No significant publication bias was detected by Deeks' funnel plot asymmetry test.</p><p><strong>Conclusion: </strong>Current LLMs demonstrate moderate discriminatory performance for identifying patients assigned to the highest-acuity triage category by the reference standard, but have limited sensitivity for these cases. LLMs may have potential as adjunctive support tools, but further prospective evaluation with patient-centered and safety-critical outcomes is required before implementation can be considered.</p>","PeriodicalId":9002,"journal":{"name":"BMC Emergency Medicine","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2026-06-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13520277/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148257187","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Diagnostic discordance and differential diagnoses of community-acquired pneumonia in the emergency department.","authors":"Susanne Simon, Jan Fuge, Christopher Alexander Hinze, Santiago Ewig, Tobias Welte, Torben Brod, Jessica Rademacher","doi":"10.1186/s12873-026-01641-5","DOIUrl":"10.1186/s12873-026-01641-5","url":null,"abstract":"<p><strong>Background: </strong>Community-acquired pneumonia (CAP) is a common reason for presentation to the emergency department (ED), but accurate diagnosis is challenging due to overlapping and often nonspecific clinical features. Data on the frequency and spectrum of alternative diagnoses in patients initially diagnosed with CAP in the ED are limited. The aim of this study was to evaluate the diagnostic concordance of an initial ED diagnosis of CAP, characterize common alternative discharge diagnoses, and analyze clinical, laboratory, imaging utilization, and vital sign parameters associated with confirmed CAP.</p><p><strong>Methods: </strong>We conducted a retrospective analysis of diagnostic concordance and differential diagnoses in 1,385 adult patients who presented to the ED of Hannover Medical School and were initially diagnosed with CAP. Initial ED diagnoses were compared with discharge diagnoses.</p><p><strong>Results: </strong>The cohort comprised 37% female and 63% male patients with a median age of 71 years (IQR 58-79). Comparison between initial ED and discharge diagnoses demonstrated that suspected CAP was confirmed in 52% (n = 663) of cases. The most common differential diagnoses were other pulmonary conditions (n = 297, 41%), cardiac conditions (n = 150, 21%), and renal conditions (n = 95, 13%). Patients with confirmed CAP showed significantly higher C-reactive protein (CRP) levels (82 mg/L [IQR 37-159] vs. 57 mg/L [IQR 22-127]; p < 0.001) and slightly higher body temperature (37.1 °C [IQR 36.4-38.0] vs. 36.8 °C [IQR 36.2-37.7]; p < 0.001) than those with alternative diagnoses.</p><p><strong>Conclusion: </strong>Only about half of patients initially diagnosed with CAP in the emergency setting had a confirmed diagnosis at discharge, indicating that CAP in this context should be regarded as a working diagnosis rather than a definitive entity. Isolated laboratory, imaging, and vital sign parameters showed limited ability to distinguish CAP from alternative diagnoses, highlighting the importance of structured reassessment after admission to confirm or revise the initial diagnosis and to reduce misclassification and unnecessary antibiotic use.</p>","PeriodicalId":9002,"journal":{"name":"BMC Emergency Medicine","volume":"26 1","pages":""},"PeriodicalIF":3.1,"publicationDate":"2026-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13263920/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148238714","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Effectiveness of out-of-hospital cardiopulmonary resuscitation in Nigeria: an evaluation of key components in the chain of survival.","authors":"Israel Kayode Kolawole, Lukman Olajide Abdur-Rahman, Shehu Abubakar Kana, Aisha Oluwabunmi Ajala, Akinyemi Aje, Olubusola Temitope Alagbe-Briggs, Yekeen Ayodele Ayoola, Nkeiruka Chigekwu Mbadiwe, Hadiza Shehu Galadanci, Josephus Kayode Ladipo, Dalhat Salahu, Arinola Adeyoola Sanusi, James Ayodele Ogunmodede, Tonia Chinyelu Onyeka, Tanimu Sambo Yusuf, Olaitan A Soyannwo, Kehinde Sunday Oluwadiya, Kene Terfa","doi":"10.1186/s12873-026-01640-6","DOIUrl":"10.1186/s12873-026-01640-6","url":null,"abstract":"<p><strong>Background: </strong>The ''Chain of Survival'' (CoS), provides a structure to evaluate an emergency response system for out-of-hospital cardiac arrest (OHCA) in any community. This CoS has not been previously evaluated in an African population. The study aims to assess the effectiveness and efficiency of OHCA resuscitation by evaluating the components of the CoS following sudden cardiac arrest in Nigeria.</p><p><strong>Methodology: </strong>This was a prospective multicenter descriptive cross-sectional exploratory survey of epidemiology and outcome of OHCA in adult Nigerians. The survey was conducted in six university teaching hospitals in the 6 geopolitical zones of Nigeria. Data was analyzed using IBM-SPSS version 25.0 (SPSS Inc., Chicago, IL, USA, and presented using tables. Continuous variables were summarized using means and standard deviation, or median and interquartile range (IQR), depending on the normality of the data. Primary outcome measures were return of spontaneous circulation (ROSC), survival to hospital admission and discharge.</p><p><strong>Results: </strong>A total of 387 OHCA patients aged between 18 and 115 years met the inclusion criteria. They consisted of 62.5% males and 37.5% females, giving a male/female ratio of approximately 1.7:1. Most (55.6%) of the arrests occurred at home. Ninety-one-point 7% (91.7%) of the arrests were witnessed. Calls were made to ambulance services but only in a third (34.6%) did an ambulance arrive. The time taken for the ambulance to arrive ranged between 10 min and 60 min, with a median of 15 min (IQR 12.5-45). Pre-hospital resuscitation was attempted in 15.2%. Pre-hospital ROSC was achieved in 3.6% of all the OHCA events, but only 1.8% survived to hospital admission and were eventually discharged.</p><p><strong>Conclusion: </strong>The emergency response service to OHCA in Nigeria is very poor due to weaknesses in the critical components of the CoS. The shortcomings observed call for well-organized, coordinated deliberate efforts to strengthen pre-hospital chain of care.</p>","PeriodicalId":9002,"journal":{"name":"BMC Emergency Medicine","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2026-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13487957/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148238683","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Magnitude, characteristics, and factors associated with severe occupational injuries among patients presenting to emergency departments in Addis Ababa, Ethiopia.","authors":"Hailemichael Mulugeta, Bente Elisabeth Moen, Teferi Abegaz, Abdisa Oli, Mengistu Mekonnen, Hana Ketema, Wakgari Deressa","doi":"10.1186/s12873-026-01643-3","DOIUrl":"10.1186/s12873-026-01643-3","url":null,"abstract":"<p><strong>Background: </strong>Occupational injuries account for more than 395 million cases and almost 3 million deaths globally each year, with the highest burden occurring in low- and middle-income countries. In Ethiopia, occupational injuries contribute substantially to emergency department visits, yet evidence on the magnitude, characteristics, and determinants remain limited. This study aimed to describe the magnitude and characteristics of occupational injuries and identify factors associated with severe injuries among patients presenting to emergency departments.</p><p><strong>Methods: </strong>A prospective hospital-based observational study was conducted at three urban public hospitals in Ethiopia. A total of 868 participants aged 18-60 years who visited emergency departments with occupational injuries were consecutively enrolled. Data was collected from October 3, 2024, to March 14, 2025, using structured interviews and clinical chart reviews. Injury severity was classified based on the World Health Organization injury surveillance guideline. Descriptive statistics summarized patient characteristics, work, and injury patterns. Poisson regression with robust variance estimation was used to identify factors associated with severe injury, and adjusted prevalence ratios with 95% confidence intervals were reported.</p><p><strong>Results: </strong>Among 5,038 injury patients, 918 (18.2%) had occupational injuries. Of these, 868 (94.6%) participated in the study. The median age was 27 years, and most participants were male (89.5%). The majority were employed in manufacturing (43.9%) and construction (24.0%). Craft and related trades (34.9%) and elementary workers (34.2%) were the most affected. Upper extremity injuries were the most common (57.0%), with lacerations (48.2%) as the leading nature of injury, followed by fractures (28.7%). The primary mechanism of injury was contact with sharp, pointed, or rough elements (43.9%), followed by falls or crashes into objects (16.6%). Among the patients, 175 (20.2%) had severe injuries. Low educational level, fall-related mechanisms, no fixed work area, and accidents due to peers and organizational causes were significantly associated with severe injury in a multivariable regression analysis.</p><p><strong>Conclusions and recommendations: </strong>Occupational injuries are a burden on emergency departments, affecting a high proportion of young, male workers in the construction and manufacturing sectors. Severe injuries were related to education, type of work, and injury mechanism. This study underscores the need for targeted workplace safety interventions.</p>","PeriodicalId":9002,"journal":{"name":"BMC Emergency Medicine","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2026-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13488590/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148222986","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Gaps and priority areas in psychosocial support for emergencies and disasters: a qualitative study in Iran.","authors":"Samira Sadat Pourhosseini, Fatemeh Molaahmadi-Hassanabadi, Mahla Iranmanesh, Vahid Yazdi-Feyzabadi, Zahra Khajeh, Nouzar Nakhaee, Ali Bahramnejad, Amirhossein Alikhani, Reza Fallah, Aliakbar Haghdoost","doi":"10.1186/s12873-026-01633-5","DOIUrl":"10.1186/s12873-026-01633-5","url":null,"abstract":"<p><strong>Background: </strong>Inefficiencies within the structures, processes, and resources associated with mental health and psychosocial support (MHPSS) can lead to adverse individual and collective health outcomes among disaster survivors. Therefore, accurately identifying the barriers to implementing these interventions is essential for strengthening the disaster response system. This study aimed to explore and extract the key challenges and recommendations related to MHPSS in disasters within the national health system in Iran.</p><p><strong>Methods: </strong>This study was conducted in December 2024 using a qualitative research design and a directed content analysis approach. Participants consisted of 20 experts in mental health, disaster management, and health policy, selected through purposive sampling. Data were collected via semi-structured, in-depth interviews, and the trustworthiness of the findings was ensured using Lincoln and Guba's criteria.</p><p><strong>Results: </strong>Nine major challenge domains were identified. At the macro governance level, a limited recognition of the importance of MHPSS and insufficient attention to the long-term psychosocial consequences of disasters were reported. Within the domains of organization and coordination, the absence of a unified command and the presence of parallel activities across agencies were identified. Structural constraints included the lack of formally approved organizational structures, inadequate infrastructure, and the absence of a clear framework for the management and integration of volunteers. In the area of human resources, key challenges comprised a shortage of psychiatrists, misalignment between workforce capacity and assigned responsibilities, and insufficient attention to the motivation and welfare of responders. Training and research gaps were noted, including insufficient pre-disasters training and limited context-specific applied research. In addition, ineffective risk communication and limited consideration of cultural and social dimensions were identified as prominent obstacles to delivering effective MHPSS interventions.</p><p><strong>Conclusions: </strong>MHPSS in disasters is confronted with complex and intersectoral challenges, the resolution of which requires a coordinated and evidence-informed approach. Enhancing policymakers' awareness, ensuring sustainable financial resources, developing needs based training programs, leveraging local human resources, and incorporating cultural considerations can substantially improve the effectiveness of MHPSS services during crises and provide a foundation for future policymaking and planning in the health system.</p>","PeriodicalId":9002,"journal":{"name":"BMC Emergency Medicine","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2026-06-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13479971/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148216297","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Artificial intelligence in prehospital assessment of acute coronary syndrome: a scoping review.","authors":"Kimia Khonakdar, Reyhaneh Sadat Faghani, Fatemeh Keyhanian, Sogand Ramezanian, Hosna Ziabakhsh Ganji","doi":"10.1186/s12873-026-01636-2","DOIUrl":"10.1186/s12873-026-01636-2","url":null,"abstract":"<p><strong>Background: </strong>Acute coronary syndrome (ACS) remains a leading cause of morbidity and mortality worldwide, where timely diagnosis is critical. Prehospital assessment is challenging due to limited diagnostic resources and high clinical uncertainty. Artificial intelligence (AI) has emerged as a potential tool to support early diagnosis, risk stratification, and triage. This scoping review aimed to map the current evidence on AI applications in the prehospital assessment of suspected ACS and to identify existing knowledge gaps.</p><p><strong>Methods: </strong>A scoping review was conducted in accordance with PRISMA-ScR guidelines. A comprehensive search of PubMed, Scopus, Web of Science, and Embase was performed up to May 2026. Studies evaluating AI-based models using prehospital data for ACS diagnosis, prediction, or triage were included.</p><p><strong>Results: </strong>19 studies involving 319,709 patients were included. AI-based models, particularly ECG-based deep learning and multimodal approaches, demonstrated promising diagnostic performance, with AUC values generally ranging from approximately 0.81 to 0.99, sensitivity from 73% to 94%, and specificity from 56% to 99%. These models improved sensitivity, reduced diagnostic variability, and enhanced triage efficiency in some settings. Risk prediction models showed moderate to good performance (AUC ~ 0.71-0.95) but were more variable. Emerging applications extended beyond diagnosis to risk stratification and decision support, including prediction of cardiogenic shock and need for revascularization.</p><p><strong>Conclusions: </strong>AI shows considerable potential to improve prehospital assessment of suspected ACS, particularly through enhanced ECG interpretation and multimodal data integration. However, current evidence remains limited by methodological constraints. Future prospective, multicenter studies with standardized approaches are essential to support clinical implementation.</p>","PeriodicalId":9002,"journal":{"name":"BMC Emergency Medicine","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2026-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13445775/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148194527","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}