Ambulance Allocation Research Articles

Applications and Performance of Machine Learning Algorithms in Emergency Medical Services: A Scoping Review.

The aim of this study was to summarize the literature on the applications of machine learning (ML) and their performance in Emergency Medical Services (EMS). Four relevant electronic databases were searched (from inception through January 2024) for all original studies that employed EMS-guided ML algorithms to enhance the clinical and operational performance of EMS. Two reviewers screened the retrieved studies and extracted relevant data from the included studies. The characteristics of included studies, employed ML algorithms, and their performance were quantitively described across primary domains and subdomains. This review included a total of 164 studies published from 2005 through 2024. Of those, 125 were clinical domain focused and 39 were operational. The characteristics of ML algorithms such as sample size, number and type of input features, and performance varied between and within domains and subdomains of applications. Clinical applications of ML algorithms involved triage or diagnosis classification (n = 62), treatment prediction (n = 12), or clinical outcome prediction (n = 50), mainly for out-of-hospital cardiac arrest/OHCA (n = 62), cardiovascular diseases/CVDs (n = 19), and trauma (n = 24). The performance of these ML algorithms varied, with a median area under the receiver operating characteristic curve (AUC) of 85.6%, accuracy of 88.1%, sensitivity of 86.05%, and specificity of 86.5%. Within the operational studies, the operational task of most ML algorithms was ambulance allocation (n = 21), followed by ambulance detection (n = 5), ambulance deployment (n = 5), route optimization (n = 5), and quality assurance (n = 3). The performance of all operational ML algorithms varied and had a median AUC of 96.1%, accuracy of 90.0%, sensitivity of 94.4%, and specificity of 87.7%. Generally, neural network and ensemble algorithms, to some degree, out-performed other ML algorithms. Triaging and managing different prehospital medical conditions and augmenting ambulance performance can be improved by ML algorithms. Future reports should focus on a specific clinical condition or operational task to improve the precision of the performance metrics of ML models.

Optimizing Ambulance Allocation in Dynamic Urban Environments: A Historic Data-Driven Approach

In this study, we present a methodology to solve the multi-period ambulance relocation problem based on historical data. We present a methodology to convert historical data in latitude–longitude coordinates into cell-based network data. Then, we propose a mixed-integer programming model that utilizes the converted data for the concomitant problem. Patient incidence is highly uncertain. Rather than simply covering historical demand, we propose a methodology that allows ambulances to reach as many locations as possible at any given time within a limited amount of time, the golden time. We experimented with real data from Seoul, South Korea, and show that the proposed mathematical model can derive an efficient ambulance operation policy with fewer ambulances.

Adaptive variable neighbourhood search approach for time-dependent joint location and dispatching problem in a multi-tier ambulance system

Location-allocation of ambulances is a critical planning problem in the efficient operation of an emergency medical services system. This work considers a joint ambulance location and dispatch problem for a multi-tier ambulance system. The proposed problem addresses three key decisions: the location of ambulance stations, allocation of ambulances to these stations, and the preference order of stations for dispatching ambulances. We consider various other important factors, such as temporal variation in demand and travel time, station-specific ambulance busy probabilities and possible relocation of ambulances over the day. A mixed-integer non-linear programming model is formulated with a survival probability-based objective function to represent the problem. A queueing-based iterative approximation approach is presented to estimate the station-level dispatch probability of ambulances. We propose an adaptive variable neighbourhood search approach to solve the problem that utilises the approximation approach to obtain the objective function. A relaxed station location problem combined with a particle swarm approach for ambulance allocation is solved to obtain an initial solution. The effectiveness of the proposed approach is validated using a dataset generated based on the city of Kolkata in India.

Estimation of the number of heat illness patients in eight metropolitan prefectures of Japan: Correlation with ambient temperature and computed thermophysiological responses.

The number of patients with heat illness transported by ambulance has been gradually increasing due to global warming. In intense heat waves, it is crucial to accurately estimate the number of cases with heat illness for management of medical resources. Ambient temperature is an essential factor with respect to the number of patients with heat illness, although thermophysiological response is a more relevant factor with respect to causing symptoms. In this study, we computed daily maximum core temperature increase and daily total amount of sweating in a test subject using a large-scale, integrated computational method considering the time course of actual ambient conditions as input. The correlation between the number of transported people and their thermophysiological temperature is evaluated in addition to conventional ambient temperature. With the exception of one prefecture, which features a different Köppen climate classification, the number of transported people in the remaining prefectures, with a Köppen climate classification of Cfa, are well estimated using either ambient temperature or computed core temperature increase and daily amount of sweating. For estimation using ambient temperature, an additional two parameters were needed to obtain comparable accuracy. Even using ambient temperature, the number of transported people can be estimated if the parameters are carefully chosen. This finding is practically useful for the management of ambulance allocation on hot days as well as public enlightenment.

Fairness over time in dynamic resource allocation with an application in healthcare

Decision making problems are typically concerned with maximizing efficiency. In contrast, we address problems where there are multiple stakeholders and a centralized decision maker who is obliged to decide in a fair manner. Different decisions give different utility to each stakeholder. In cases where these decisions are made repeatedly, we provide efficient mathematical programming formulations to identify both the maximum fairness possible and the decisions that improve fairness over time, for reasonable metrics of fairness. We apply this framework to the problem of ambulance allocation, where decisions in consecutive rounds are constrained. With this additional complexity, we prove structural results on identifying fair feasible allocation policies and provide a hybrid algorithm with column generation and constraint programming-based solution techniques for this class of problems. Computational experiments show that our method can solve these problems orders of magnitude faster than a naive approach.

Optimized Ambulance Allocation Using Hybrid PSOGA for Improving the Ambulance Service

Emergency Medical Service (EMS) is an integral part of the healthcare system that works dedicatedly to save the lives of people. The prime responsibility of any EMS provider is to offer a timely response to the person in need. The timely assistance increases the chances of survivability of a person. In India, escalating count of road accidents has increased the demand for ambulance services to provide pre-hospital treatment or transportation of victims to the hospital. This paper presents a new optimization strategy of Hybrid Particle Swarm Optimization and Genetic Algorithm (HPSOGA) for ambulance allocation to reduce the ambulance response time. Considering a set of assumptions, the authors have applied the new strategy for allocating 50 ambulances to 11 base stations in Southern Delhi. The working environment of EMS which includes stochastic requests, travel time, and dynamic traffic conditions have been taken into account to attain accurate results. The new optimization strategy of HPSOGA has been implemented in a MATLAB environment to find an optimized allocation plan with minimum response time. With the proposed algorithm the authors have been able to reduce the average response time by 11.61%. The paper also presents the comparison of HPSOGA, Genetic Algorithm (GA), and Particle Swarm Optimization (PSO) for the stated problem. The algorithms are compared in terms of objective value (response time), convergence rate, and constancy repeatability to conclude that HPSOGA performs better than the other two algorithms.

An improved EMS simulation-optimization model with Poisson mixture distribution

A Discrete Event System (DES) simulation and optimization model is proposed for the ambulance allocation problem in an Emergency Medical Service (EMS) system. The accuracy of the proposed model was improved by estimation of input parameters using the Poisson mixture model and the Expectation Maximization Algorithm. The results were proven by Mann–Whitney and Kolmogorov–Smirnov tests. The DES model was run by the OptQuest program embedded in Arena software. The response times of the cases within the urban and rural regions were improved by 40% and 45%, respectively, and the station success rates in urban and rural areas were raised to 95% and 96%, respectively. Our results indicated that the number of ambulances must be revised, and their allocations to stations in the real system need to be reorganized to achieve the required EMS system performance standards.

Integrating Spatial Risk Factors with Social Media Data Analysis for an Ambulance Allocation Strategy: A Case Study in Bangkok

Emergency medical service (EMS) base allocation plays a critical role in emergency medical service systems. Fast arrival of an EMS unit to an incident scene increases the chance of survival and reduces the chance of victim disability. However, recently, the allocation strategy has been performed by experts using past data and experiences. This may lead to ineffective planning due to a lack of consideration of a recent and relevant data, such as disaster events, population density, public transportation stations, and public events. Therefore, we propose an approach of the integration of using spatial risk factors and social media factors to identify EMS bases. These factors are combined into a single domain by using the kernel density estimation technique, resulting in a heatmap. Then, the heatmap is used in a modified maximizing covering location problem with a heatmap (MCLP-Heatmap) to allocate ambulance base. To acquire recent data, social media is then used for collecting road accidents, traffic, flood, and fire incidents. Additionally, another data source, spatial risk information, is collected from Bangkok GIS. These data are analyzed using the kernel density estimation method to construct a heatmap before being sent to the MCLP-heatmap to identify EMS bases in the area of interest. In addition, the proposed integrated approach is applied to the Bangkok area with a smaller number of EMS bases than that of the existing approach. The simulated results indicated that the number of covered EMS requests was increased by 3.6% and the number of ambulance bases in action was reduced by approximately 26%. Additionally, the bases defined by the proposed approach covered more area than those of the existing approach.

The intelligent Traffic Management System for Emergency Medical Service Station Location and Allocation of Ambulances.

In the present study, the optimization of medical services considering the role of intelligent traffic management is of concern. In this regard, a two-objective mathematical model of a medical emergency system is assessed in order to determine the location of emergency stations and determine the required number of ambulances to be allocated to the station. The objective functions are the maximization of covering the emergency demands and minimization of total costs. Moreover, the use of an intelligent traffic management system to speed up the ambulance is addressed. In this regard, the proposed two-objective mathematical model has been formulated, and a robust counterpart formulation under uncertainty is applied. In the proposed method, the values of the objective function increase as the problem becomes wider and, with a slight difference in large dimensions, converge in terms of the solution. The numerical results indicate that, as the problem's complexity increases, the robust optimization method is still effective because, with the increasing complexity of the problem, it can still solve large-scale problems in a reasonable time. Moreover, the difference between the value of the objective function in the proposed method and the presence of uncertainty parameters is very small and, in large dimensions, is quite logical and negligible. The sensitivity analysis shows that, with increasing demand, both the number of ambulances required and the amount of objective function have increased significantly.

Ambulance location under temporal variation in demand using a mixed coded memetic algorithm

Emergency medical services (EMS) are among the most important services in any society due to their role in saving people’s lives and reducing morbidities. The location of ambulance stations and the allocation of ambulances to the stations is an important planning problem for any EMS system to ensure adequate coverage while minimising the response time. This study considers a mixed-integer programming model that determines the ambulance locations by considering the time of day variations in demand. The presented model also considers heterogeneous performance measures based on survival function and coverage for different patient types with varying levels of urgency. A memetic algorithm based-approach that applies a mixed chromosome representation for solutions is proposed to solve the problem. Our computational results indicate that neglecting time-dependent variation of demand can underestimate the number of ambulances required by up to 15% during peak demand. We also demonstrate the effectiveness of the proposed solution approach in providing good quality solutions within a reasonable time.

Modeling location–allocation of emergency medical service stations and ambulance routing problems considering the variability of events and recurrent traffic congestion: A real case study

One of the most important and common criteria for evaluating the emergency medical systems is the response time, which is a function of the availability of an ambulance at the time of the request and the time that it takes for the ambulance to arrive at the call location. In this study, an optimization model is proposed to deal with the problem of the emergency medical service stations’ location and ambulance allocation. In order to capture the impacts of uncertainty in the network and obtain more realistic results, it is assumed that medical aid demands from any location in the city at any time slot of the day have a probabilistic distribution. In addition, to consider the traffic fluctuations in the modeling process, it is assumed that the arrival time to the request location is a time dependent variable. To deal with the complexity of the proposed approach and find optimal solutions in a reasonable execution time, some heuristic algorithms are suggested to solve the ambulance routing problem and the proposed non-linear integer model. To show the applicability of proposed models and algorithms in large-scale networks, the models and algorithms have been applied to the emergency medical system of the city of Isfahan, Iran. Three different scenarios are defined to improve the performance of the emergency medical services in Isfahan. The results show that relocating emergency medical service stations and reallocating ambulances will lead to significant improvements in both response time and coverage area in Isfahan.

Improving Lagos State emergency medical services by analysing road traffic accident data, response time, and efficient allocation of ambulances

BackgroundEmergency medical services (EMS) play a critical role in the response to road traffic accidents (RTAs) by providing critical prehospital care to RTA victims, and thus helping to reduce the severity of injuries and casualties from RTAs. Analysing the efficiency of such systems and optimising the service (often with insufficient resources) would be highly beneficial to inform operating guidelines. In this study, we aimed to assess the ambulance utilisation rate for RTAs and provide insights about the system's efficiency and utilisation metrics in Lagos State, Nigeria. MethodsWe received hospital capacity information (type of hospital [eg, tertiary] and number of beds, nurses, operating rooms, and so on) from hospital survey data in Lagos. Additionally, we received RTA-specific intervention forms from the Lagos State Ambulance Service. With the limited amount of historical data, we highlighted methods to estimate the system parameters (eg, arrival rate, service rate, and so on) of RTA victims at various hospitals in Lagos. We also developed a parametric model and applied approximate dynamic programming approach for ambulance dispatch and location optimisation with a fixed number of base stations. Furthermore, our routing approach was accompanied by directions from OpenRouteService and queue analysis to determine the most appropriate hospital near an RTA for the EMS systems in Lagos. FindingsUsing patient-queue based wait-time analysis, we found that in over 80% of cases, one of the nearest three hospitals was the most appropriate recommendation for patient delivery. This exponentially decays with the next closest hospitals. Additionally, we found that optimising the ambulance relocation method, where the ambulance returns to a base selected by our model as opposed to its dedicated base or a random base, can reduce the average response time of the EMS system by 8%, or 3·5 min (from 41 min to 38 min). InterpretationAppropriate placement of mobile resources (ie, ambulances, health-care booths, and so on) can help to lower the response time of EMS systems in addressing RTAs. Similarly, optimal routing of patients to the most well prepared and nearby hospitals would significantly increase the system's efficacy and improve health outcomes. Our findings can provide valuable insight into this and further inform resource allocation and guidelines for health systems, by identifying those hospitals that have the highest burden of RTA victims and those that provide the most efficient care in a resource-limited setting. FundingNational Institutes of Health (1R21TW010991–01A1).

Ambulances Deployment Problems: Categorization, Evolution and Dynamic Problems Review

In this paper, an analytic review of the recent methodologies tackling the problem of dynamic allocation of ambulances was carried out. Considering that state-of-the-art is moving to deal with more extensive and dynamic problems to address in a better way real-life instances, this research looks to identify the evolution and recent applications of this kind of problem once the basic models are explored. This extensive review allowed us to identify the most recent developments in this problem and the most critical gaps to be addressed. In this sense, it is essential to point out that the dynamic location of emergency medical services (EMS) is nowadays a relevant topic considering its impact on the healthcare system outcomes. Issues related to forecasting, simulation, heterogeneous fleets, robustness, and solution speed for real-life problems, stand out in the identified gaps. Applications of machine learning the deployment challenges during epidemic outbreaks such as SARS and COVID-19 were also explored. At the same time, a proposed notation tries to tackle the fact that the word problem in this kind of work refers to a model on many occasions. The proposed notation eases the comparison between the different model proposals found in the literature.

Optimally Allocating Ambulances in Delhi using Mutation based Shuffled Frog Leaping Algorithm

This paper presents a reliable and competent evolutionary-based approach for improving the response time of Emergency Medical Service (EMS) by efficiently allocating ambulances at the base stations. As the prime objective of EMS is to save people's lives by providing them with timely assistance, thus increasing the chances of a person's survivability, this paper has undertaken the problem of ambulance allocation. The work has been implemented using the proposed mutation-based Shuffled Frog Leaping Algorithm (mSFLA) to provide an optimal allocation plan. The authors have altered the basic SFLA using the concept of mutation to improve the quality of the solution obtained and avoid being trapped in local optima. Considering a set of assumptions, the new algorithm has been applied for allocating 50 ambulances among 11 base stations in Southern Delhi. The working environment of EMS, which includes stochastic requests, travel time, and dynamic traffic conditions, has been considered to attain accurate results. The work has been implemented in the MATLAB simulation environment to find an optimized allocation plan with a minimum average response time. The authors have reduced the average response time by 12.23% with the proposed algorithm. The paper also compares mSFLA, Genetic Algorithm (GA), and Particle Swarm Optimization (PSO) for the stated problem. The algorithms are compared in terms of objective value (average response time), convergence rate, and constancy repeatability to conclude that mSFLA performs better than the other two algorithms.

Prediction of the number of heatstroke patients transported by ambulance in Japan’s 47 prefectures: proposal of heat acclimatization consideration

The incidence of heatstroke is affected by various meteorological variables. However, previous studies in Japan have mainly investigated and adopted a single temperature metric or composite index for their analyses. Herein, we conducted a time series study through multivariate analysis of different weather conditions simultaneously, in order to analyze the relative importance of meteorological variables to determine the number of heatstroke patients transported by ambulance in all of Japan’s 47 prefectures. We proposed a method that considers heat acclimatization, which has been found to impact the heatstroke, by manipulating certain meteorological variables. For the heatstroke data, we utilized the secondary data provided by the Fire and Disaster Management Agency, Japan. The time period considered was from May 2015 to September 2019. All calculations were performed using R 3.5.1. For the analysis, the machine learning method of random forest (RF) was applied. The results showed that the relative temperature (RelTemp), which represents heat acclimatization, had the highest ranking among all the meteorological variables studied. Then, we developed the exponential model and the RF model to predict the number of heatstroke patients transported by ambulance by adopting the highly ranked meteorological variables including RelTemp as explanatory variables. To confirm the effectiveness of heat acclimatization, we also developed the exponential model and the RF model both without RelTemp (instead, with maximum temperature). According to the results, the R2 values of the exponential and the RF models, including RelTemp, were 0.76 and 0.74, respectively, and those of the exponential and the RF models, excluding RelTemp, were 0.68 and 0.67, respectively. We confirmed the effectiveness of considering heat acclimatization via RelTemp and found that the exponential model with RelTemp provided the higher accuracy. Better predictions by the exponential model with RelTemp would contribute to better preemptive allocation of ambulances and medical staff in medical facilities.

Social implementation and intervention with estimated morbidity of heat-related illnesses from weather data: A case study from Nagoya City, Japan

The estimation of heat-related illness cases is a key factor in proposing and implementing suitable intervention strategies and healthcare resource management. This paper proposes new frameworks to estimate the number of patients with heat-related illnesses by administrative wards in Nagoya City using 2014–2019 data. The proposed frameworks are based on the derivation of estimation formulae and machine learning. The daily residual estimation error in the 16 wards was less than one person with both the frameworks. The daily working time average ambient temperature may yield a better correlation than the daily average temperature or daily highest temperature with the number of patients transported by an ambulance from outdoor sites. The results also indicate that patients transported from indoor sites are influenced by earlier ambient conditions over approximately 50 days. In contrast, those transported from outdoor sites are influenced by a relatively short period (20 days), which may correspond to heat adaptation. The frameworks provide a better understanding of the different factors that would lead to an accurate prediction of the number of cases of heat-related patients from weather forecasts. These findings would lead to efficient ambulance allocation as well as public awareness on hot days to suppress heat-related morbidity.

Enhanced coverage by integrating site interdependencies in capacitated EMS location models

In order to allocate limited resources in emergency medical services (EMS) networks, mathematical models are used to select sites and their capacities. Many existing standard models are based on simplifying assumptions, including site independency and a similar system-wide busyness of ambulances. In practice, when a site is busy, a call is forwarded to another site. Thus, the busyness of each site depends not only on the rate of calls in the surrounding area, but also on interactions with other facilities. If the demand varies across the urban area, assuming an average system-wide server busy fraction may lead to an overestimation of the actual coverage. We show that site interdependencies can be integrated into the well-known Maximum Expected Covering Location Problem (MEXCLP) by introducing an upper bound for the busyness of each site. We apply our new mathematical formulation to the case of a local EMS provider. To evaluate the solution quality, we use a discrete event simulation based on anonymized real-world call data. Results of our simulation-optimization approach indicate that the coverage can be improved in most cases by taking site interdependencies into account, leading to an improved ambulance allocation and a faster emergency care.

Empirical Spatial Density-Based Emergency Medical Service Demand Forecast for Ambulance Allocation

In a previous study, we solved the two-fold dynamic ambulance allocation problem, including forecasting the distribution of Emergency Medical Service (EMS) requesters and dynamically allocating ambulances according to the predicted distribution of requesters. In the definition of the coverage region, the Euclidean distance was used, which is not suitable for measuring the length of a route between two places. This study improved on the previous one by redefining the coverage region for practical application and providing a simulation model to verify the effectiveness of the proposed ambulance allocation method. The simulation results show the proposed allocation method providing higher demand coverage rates and shorter response distances than the official allocation.

Characteristics of Emergency Medical Services Utilized by Elderly Residents in Nursing Homes

This study aims to analyze the characteristics of emergency medical services (EMS) utilization among elderly patients divided into two groups depending on place of living: nursing homes and places other than nursing homes. The data includes patients aged 65 years old and over for whom ambulances were requested by the 119 Dispatch Center in Gyeonggi Province from January 1st to December 31st, 2018. Statistical analysis was performed using IBM SPSS Statistics 21.0. The findings showed that EMS ambulances were requested more frequently for female patients in nursing homes than males in other places. Brain disease was the most common medical history of the EMS users at nursing homes (P=0.000). Also, critical medical conditions, such as cardiac arrest (5.4%), altered mental status (16.4%), difficulty breathing (18.6%), and fever (19.2%), were found more than twofold higher among the EMS patients in nursing homes, which were classified as emergency by EMS crews. This study suggests a review and amendment of the legal standards regarding support for emergency medical providers and allocation of ambulances.

Rapid reorganization of the Milan metropolitan public safety answering point operations during the initial phase of the COVID-19 outbreak in Italy.

ObjectiveTo quantify how the first public announcement of confirmed coronavirus disease 2019 (COVID‐19) in Italy affected a metropolitan region's emergency medical services (EMS) call volume and how rapid introduction of alternative procedures at the public safety answering point (PSAP) managed system resources.MethodsPSAP processes were modified over several days including (1) referral of non‐ill callers to public health information call centers; (2) algorithms for detection, isolation, or hospitalization of suspected COVID‐19 patients; and (3) specialized medical teams sent to the PSAP for triage and case management, including ambulance dispatches or alternative dispositions. Call volumes, ambulance dispatches, and response intervals for the 2 weeks after announcement were compared to 2017–2019 data and the week before.ResultsFor 2 weeks following outbreak announcement, the primary‐level PSAP (police/fire/EMS) averaged 56% more daily calls compared to prior years and recorded 9281 (106% increase) on Day 4, averaging ∼400/hour. The secondary‐level (EMS) PSAP recorded an analogous 63% increase with 3863 calls (∼161/hour; 264% increase) on Day 3. The COVID‐19 response team processed the more complex cases (n = 5361), averaging 432 ± 110 daily (∼one‐fifth of EMS calls). Although community COVID‐19 cases increased exponentially, ambulance response intervals and dispatches (averaging 1120 ± 46 daily) were successfully contained, particularly compared with the week before (1174 ± 40; P = 0.02).ConclusionWith sudden escalating EMS call volumes, rapid reorganization of dispatch operations using tailored algorithms and specially assigned personnel can protect EMS system resources by optimizing patient dispositions, controlling ambulance allocations and mitigating hospital impact. Prudent population‐based disaster planning should strongly consider pre‐establishing similar highly coordinated medical taskforce contingencies.