GPU-Accelerated Slime Mould Algorithm for Urgent Transportation in Disaster Response: A COVID-19 Application

Integrating the ambulance dispatching and relocation problems to maximize system’s preparedness

A decomposition-based multiobjective evolutionary algorithm using Simulated Annealing for the ambulance dispatching and relocation problem during COVID-19

Accurate and robust forecasting of Emergency Medical Services (EMS) demand is crucial for ensuring timely ambulance dispatch and efficient resource allocation, particularly in low-resource public health systems, such as those in India. While most prior EMS forecasting studies have focused on urban settings in developed countries with rich, granular data, limited research has explored district-level forecasting using real-world ambulance dispatch data from India. Moreover, existing models often trade off robustness for accuracy or rely on complex black-box architectures, limiting their interpretability and real-world deployment. This study examines whether a heterogeneous ensemble of interpretable and complementary learners can outperform traditional and state-of-the-art regressors for district-level EMS forecasting, utilizing limited real-world features. To address this challenge, we propose EM-LR (Ensembled Meta-Learner with Linear Regression), a meta-learning framework that integrates four diverse base models-Lasso Regression, Support Vector Regression (SVR), Multilayer Perceptron (MLP), and Extreme Gradient Boosting (XGB)-via a linear regression meta-learner. Unlike prior meta-learners that stack similar tree-based or linear models, EM-LR combines low-variance, diverse learners to enhance robustness while maintaining model interpretability through SHAP-based feature analysis and transparent ensemble weights. Using only temporal and meteorological inputs, EM-LR forecasts daily EMS call volumes across five diverse districts in the state of Uttar Pradesh. We benchmark EM-LR against traditional models and recent advanced variants, including Twin Bounded Least Squares Support Vector Regression (TBLSSVR), Asymmetric-Huber based Extreme Learning Machine (AHELM), and Mexican-Hat Kernelized Large Margin Distribution Machine-based Regression (MHKLDMR), demonstrating superior accuracy and reduced prediction variance. Experimental results show up to 9.5% reduction in RMSE and over 40% variance reduction. EM-LR thus offers a scalable and interpretable forecasting solution tailored to the operational constraints of developing public health systems, supporting data-driven emergency planning and equitable healthcare delivery.

This comprehensive review explores the role of oral surgery in disaster management, highlighting its various phases of disaster response. The study uses a qualitative literature review to analyze current practices, challenges, and future directions in integrating oral surgical expertise into disaster preparedness and response frameworks. Findings reveal that oral surgeons contribute significantly to patient care in disaster scenarios. Integrating oral surgery in disaster management remains inconsistent globally, including oral surgeons in response teams. It identifies inadequate specialized training, limited awareness among disaster planning authorities, and logistical difficulties in deploying oral surgical resources. Technological advancements offer promising solutions to enhance the reach and effectiveness of oral surgical care in disaster settings. It underscores the psychological impact of oral and maxillofacial injuries on disaster survivors, emphasizing the importance of timely interventions for mental health and social reintegration. Ethical considerations surrounding resource allocation in disaster scenarios are examined. The review concludes by proposing recommendations for policy development, training enhancement, interdisciplinary collaboration, and technology adoption to improve oral surgery in disaster management. This research contributes to a growing body of evidence supporting the essential role of oral surgery in comprehensive disaster response strategies and advocates for its fuller incorporation into global disaster management frameworks.

AimPrehospital critical care for out-of-hospital cardiac arrest (OHCA) is a complex and largely unproven intervention. During research to examine this intervention, we noted significant differences in stakeholders’ views about research,...

In pre-hospital health care the call center plays an important role in the coordination of emergency medical services (EMS). An EMS call center handles inbound requests for EMS and dispatches an ambulance if necessary. The time needed for triage and dispatch is part of the total response time to the request, which, in turn, is an indicator for the quality of EMS. Calls entering an efficient EMS call center must have short waiting times, centralists should perform the triage efficiently and the dispatch of ambulances must be adequate and swift. This paper presents a detailed discrete event simulation model for EMS call centers. The model provides insight into the EMS call center processes and can be used to address strategic issues, such as capacity and workforce planning. We analyse results of the model that are based on real EMS call center data to illustrate the usefulness of the model.

A simulation and optimisation package for emergency medical services

Objectives:Patients who frequently call ambulance services are a vulnerable yet heterogeneous population with unmet multiple and complex physical health, mental health and/or social care needs. In this article, we report the challenges that the COVID-19 pandemic has introduced for ambulance services across the UK when managing frequent callers, and reflect on how existing systems and practices are adapting to support changing patient needs.Methods:Data reported in this article comprise reflections from the frequent caller leads in each ambulance service in the UK. All data were provided between 23 April 2020 and 1 May 2020, shortly after the peak of the outbreak in the UK. A single anonymised case study is also reported to illustrate how the pandemic is affecting people’s circumstances and contributing to frequent caller behaviour.Results:Ambulance services are observing changes to the frequent caller population, with many new frequent callers due to health anxiety caused or exacerbated by the pandemic. Management of frequent callers is also changing, with multidisciplinary and multi-agency working becoming more challenging due to decreased access to external services, whether in social care or the community and voluntary sector, and the redeployment of ambulance service staff. There is also decreased face-to-face contact with frequent callers, meaning that opportunities to deliver person-centred care are reduced. However, the introduction or increased use of tele/video conferencing with other organisations has mitigated some of these challenges, and in some cases has improved engagement among external organisations.Conclusions:Health anxieties, lack of access to other health, social and community and voluntary sector services and exacerbations of social isolation and/or loneliness have reportedly contributed to changing behaviour among frequent callers. The COVID-19 pandemic has also affected how ambulance services have been able to manage frequent callers. Ambulance services should continue to engage with external organisations to aid the delivery of person-centred care, particularly organisations with experience in multiple complex needs such as mental health, social isolation and/or loneliness. Future research should examine the consequences of the pandemic for frequent users of ambulance services, and how these impact on the wider health and care community.

Introduction: Nepal is highly susceptible to natural disasters, including earthquakes, floods, and landslides, which have been exacerbated by climate change. General Practitioners (GPs) are often the first point of contact in affected communities, playing a crucial role in managing the health consequences of such calamities. This study explores the role of GPs in disaster management in Nepal, with a particular focus on preparedness, response, and recovery phases. Methods: A review of current literature, policy documents, and field data was conducted to assess GPs’ roles, knowledge of disaster medicine, and the skills required for effective disaster response. Additionally, a gap analysis was performed to evaluate current skills and the specific needs of GPs in disaster situations. The study was undertaken in partnership with Saving Lives International – a UK charity. Results: The findings highlight that Nepal GPs have been trained in triaging injuries, providing essential primary care, and delivering essential mental health support in post-disaster settings. However, gaps were identified in areas such as quality and outcomes assessments, disaster medicine preparedness training, emergency response coordination, field medicine, pre-hospital trauma care, and impact on mental health. It underscores the importance of integrating GPs into disaster management frameworks in Nepal, emphasizing the collaboration with government agencies, non-governmental organizations (NGOs), and community leaders. Training in disaster medicine and response protocols, as well as fostering community resilience, were identified as key areas of improvement. Conclusion: Enhancing GPs’ involvement in disaster management through structured training programs and resource allocation can improve healthcare outcomes in vulnerable communities, particularly during the recovery phase. Leveraging the local knowledge and established relationships, GPs can enhance the overall efficacy of disaster response efforts. The study calls for strategic investment in GP disaster preparedness to build a more resilient healthcare system capable of responding to the escalating threat of natural disasters in Nepal.

Many-core framework, represented by Graphic Processing Unit (GPU), has been becoming more popular in scientific computing and data analysis, and Compute Unified Device Architecture (CUDA) allows developers to carry out computation on GPUs more conveniently. Matrix operation is one of the most important application scenarios of GPU computation and CUDA, widely appearing in domains like graph applications and artificial intelligence. This paper focuses on accelerating matrix power operation (MPO) process, which appears in many engineering problems and may be time-consuming when the scale of matrixes is large, with GPUs and CUDA. In this paper, three techniques are used to speed up the MPO process: matrix parallel reduction, matrix parallel multiplication and CUDA dynamic parallelism. The experiments were carried out on NVIDIA RTX 2080 Super and Intel(R) Core(TM) i7-10750H. The code is compiled and executed in Visual Studio 2019 community, the GPU driver version is 461.40, the CUDA version is 11.1, and the NVCC version is 11.1.74. With all three techniques, the MPO process can get hundreds of times speedup compared with the sequential multiplication process executed by Eigen library, even though the code of algorithm is hardly optimized. Moreover, with the number of power increasing, the efficiency of algorithm can be even higher because of the relatively fixed time consumed in data transmission and GPU memory allocation.

Out-of-hospital cardiac arrest (OHCA) is a challenge for medical personnel, especially in the current COVID-19 pandemic, where medical personnel should perform resuscitation wearing full personal protective equipment. This study aims were to assess the characteristics and outcomes of adults who suffered an OHCA in the COVID-19 pandemic treated by emergency medical service (EMS) teams. All EMS-attended OHCA adults over than 18 years in the Polish EMS registry were analyzed. The retrospective EMS database was conducted. EMS interventions performed between March 1, and April 30, 2020 were retrospectively screened. In the study period EMS operated 527 times for OHCA cases. The average age of patients with OHCA was 67.8 years. Statistically significantly more frequently men were involved (64.3%). 298 (56.6%) of all OHCA patients had resuscitation attempted by EMS providers. Among resuscitated patients, 73.8% were cardiac etiology. 9.4% of patients had return of spontaneous circulation, 27.2% of patients were admitted to hospital with ongoing chest compression. In the case of 63.4% cardiopulmonary resuscitation was ineffective and death was determined. The present study found that OHCA incidence rate in the Masovian population (central region of Poland) in March-April 2020 period was 12.2/100,000 adult inhabitants. Return of spontaneous circulation in EMS was observed only in 9.4% of resuscitated patients. The presence of shockable rhythms was associated with better prognosis. The prehospital mortality, even though it was high, did not differ from those reported by other studies.

Background An ambulance traffic crash not only leads to injuries among emergency medical service (EMS) professionals but also injures patients or their companions during transportation. We aimed to describe the incidence of ambulance crashes, seating location, seatbelt use for casualties (ie, both fatal and nonfatal injuries), ambulance safety efforts, and to identify factors affecting the number of ambulance crashes in Japan. Methods We conducted a nationwide survey of all fire departments in Japan. The survey queried each fire department about the number of ambulance crashes between January 1, 2017, and December 31, 2019, the number of casualties, their locations, and seatbelt usage. Additionally, the survey collected information on fire department characteristics, including the number of ambulance dispatches, and their safety efforts including emergency vehicle operation training and seatbelt policies. We used regression methods including a zero-inflated negative binomial model to identify factors associated with the number of crashes. Results Among the 726 fire departments in Japan, 553 (76.2%) responded to the survey, reporting a total of 11,901,210 ambulance dispatches with 1,659 ambulance crashes (13.9 for every 100,000 ambulance dispatches) that resulted in a total of 130 casualties during the 3-year study period (1.1 in every 100,000 dispatches). Among the rear cabin occupants, seatbelt use was limited for both EMS professionals (n = 3/29, 10.3%) and patients/companions (n = 3/26, 11.5%). Only 46.7% of the fire departments had an internal policy regarding seatbelt use. About three-fourths of fire departments (76.3%) conducted emergency vehicle operation training internally. The output of the regression model revealed that fire departments that conduct internal emergency vehicle operation training had fewer ambulance crashes compared to those that do not (odds of being an excessive zero −2.20, 95% CI: −3.6 to −0.8). Conclusion Two-thirds of fire departments experienced at least one crash during the study period. The majority of rear cabin occupants who were injured in ambulance crashes were not wearing a seatbelt. Although efforts to ascertain seatbelt compliance were limited, Japanese fire departments have attempted a variety of methods to reduce ambulance crashes including internal emergency vehicle operation training, which was associated with fewer ambulance crashes.

Background:Emergency medical services (EMS) encounters with palliative care patients present unique operational challenges. As EMS providers increasingly care for individuals with life-limiting illnesses, understanding the intersection of emergency care and palliative medicine has become essential to optimizing healthcare delivery.Objective:This study examines EMS operational metrics, resource allocation patterns, and clinical outcomes among palliative care patients in Thailand.Methods:This retrospective analysis study investigated operational times, resource utilization, and clinical outcomes in palliative care patients utilizing EMS services, derived from electronic medical records and EMS documentation. This study was conducted at the Srinagarind Hospital EMS unit from October 2019 to September 2024. All patients diagnosed with palliative care (ICD-10 code Z51.5) who utilized EMS services were included.Results:Palliative care patients represented 6.9% (N = 340) of total EMS utilization (N = 4520), with cases increasing from 51 patients (15.0%) in 2019–2020 to 89 patients (26.2%) in 2023–2024. The median age was 72 years, with 62.9% male patients. Palliative care patients demonstrated significantly prolonged EMS operational times: activation (1.51 min vs 1.27 min), response (10.21 min vs 9.35 min), and scene time (22.05 min vs 10.02 min, p < 0.001). Resource utilization showed higher rates of pain medication administration (30.88% vs 7.79%) and exclusive use of comfort-focused interventions. Patient outcomes revealed significantly higher discharge rates.Conclusion:Palliative care patients utilizing EMS services represent a distinct population requiring specialized operational approaches. Extended scene times reflect appropriate symptom-focused care delivery rather than rapid transport protocols. Higher discharge rates validate the EMS role as a symptom management bridge.

BackgroundEfficient resource distribution is important. Despite extensive research on response timings within ambulance services, nuances of time from unit dispatch to becoming available still need to be explored. This study aimed to identify the determinants of the duration between ambulance dispatch and readiness to respond to the next case according to the patients’ transport decisions.MethodsTime from ambulance dispatch to availability (TDA) analysis according to the patients’ transport decision (Transport versus Non-Transport) was conducted using R-Studio™ for a data set of 93,712 emergency calls managed by a Middle Eastern ambulance service from January to May 2023. Log-transformed Hazard Ratios (HR) were examined across diverse parameters. A Cox regression model was utilised to determine the influence of variables on TDA. Kaplan–Meier curves discerned potential variances in the time elapsed for both cohorts based on demographics and clinical indicators. A competing risk analysis assessed the probabilities of distinct outcomes occurring.ResultsThe median duration of elapsed TDA was 173 min for the transported patients and 73 min for those not transported. The HR unveiled Significant associations in various demographic variables. The Kaplan–Meier curves revealed variances in TDA across different nationalities and age categories. In the competing risk analysis, the ‘Not Transported’ group demonstrated a higher incidence of prolonged TDA than the ‘Transported’ group at specified time points.ConclusionsExploring TDA offers a novel perspective on ambulance services’ efficiency. Though promising, the findings necessitate further exploration across diverse settings, ensuring broader applicability. Future research should consider a comprehensive range of variables to fully harness the utility of this period as a metric for healthcare excellence.Supplementary InformationThe online version contains supplementary material available at 10.1186/s12873-024-00992-1.

BackgroundChest pain is a frequent cause of health care contacts. We examined the prehospital management, in-hospital discharge diagnoses, and mortality of patients calling a non-emergency and emergency medical service with chest pain.MethodsThe Copenhagen Emergency Medical Services (EMS) consists of a non-emergency medical helpline (calls to 1813) and emergency medical service (1-1-2 calls). We included all calls to the Copenhagen EMS with a primary complaint of chest pain from 2014 to 2018 in Copenhagen, Denmark. The outcomes were: emergency response (ambulance dispatch, other transports/self-transport/home visits, self-care, and unknown/cancelled response), in-hospital diagnosis within 7 days after the call (cardiovascular, pulmonary, or other non-cardiovascular/pulmonary) and 30-day mortality.ResultsAmong 4,834,071 calls, 91,671 were registered with chest pain at the Copenhagen EMS. The first call for each patient was kept for analysis (n = 66,762). In total, 91.4% were referred to the hospital, 75.8% (n = 50,627) received an ambulance and 15.6% (n = 10,383) received other transport/self-transport/home visits. Overall, 26.9% (n = 17,937) were diagnosed with a cardiovascular disease, 5.2% (n = 3,490) a pulmonary disease, 52.8% (n = 35.242) other non-cardiovascular/pulmonary disease, and 15.1% (n = 10,093) received no diagnosis. Among ambulance-transported patients, the prevalence of cardiovascular discharge diagnoses was higher (32.1%) and fewer received no diagnosis (11.0%). Cardiovascular disease was less prevalent among patients not transported by ambulance and patients not referred to hospital at all (2-13.4%) and in patients ≤ 40 years of age (< 10%). The 30-day mortality was below 5% regardless of diagnosis (0.6-4%), and 65,704 (98.4%) were still alive 30 days later.ConclusionNearly all patients calling with chest pain were referred for treatment. Among ambulance-transported patients, around half of the patients did not have a cardiovascular/pulmonary disease. While current practices appear reasonable, improved differentiation of chest pain patients in telephone consultations could potentially both improve the treatment and management of these patients and reduce the in-hospital burden of non-acute chest pain consultations.