Accident Management Research Articles

WITHDRAWN: Wilderness Medical Society Clinical Practice Guidelines for Prevention and Management of Avalanche and Nonavalanche Snow Burial Accidents: 2024 Update

To provide guidance to the general public, clinicians, and avalanche professionals about best practices, the Wilderness Medical Society convened an expert panel to revise the evidence-based guidelines for the prevention, rescue, and resuscitation of avalanche and nonavalanche snow burial victims. The original panel authored the Wilderness Medical Society Practice Guidelines for Prevention and Management of Avalanche and Nonavalanche Snow Burial Accidents in 2017. A second panel was convened to update these guidelines and make recommendations based on quality of supporting evidence.

Main outcomes of the Phebus FPT1 uncertainty and sensitivity analysis in the EU-MUSA project

The Management and Uncertainties of Severe Accidents (MUSA) project was funded in HORIZON 2020 and is coordinated by CIEMAT (Spain). The project aims at consolidating a harmonized approach for the analysis of uncertainties and sensitivities associated with Severe Accidents (SAs) analysis, focusing on source term figures of merit. The Application of Uncertainty Quantification (UQ) Methods against Integral Experiments (AUQMIE – Work Package 4 (WP4)), led by ENEA (Italy), was devoted to apply and test UQ methodologies adopting the internationally recognized PHEBUS FPT1 test. FPT1 was chosen to test UQ methodologies because, even though it is a simplified SA scenario, it was representative of the in-vessel phase of a severe accident initiated by a break in the cold leg of a PWR primary circuit.WP4 served as a platform to identify and discuss the issues encountered in the application of UQ methodologies to SA analyses (e.g. discuss the UQ methodology, perform the coupling between the SA codes and the UQ tools, define the results post-processing methods, etc.). The purpose of this paper is to describe the MUSA PHEBUS FPT1 uncertainty application exercise with the related specifications and the methodologies used by the partners to perform the UQ exercise. The main outcomes and lessons learned of the analysis are: scripting was in general needed for the SA code and uncertainty tool coupling and to have more flexibility; particular attention should be devoted to the proper choice of the input uncertain parameters; outlier values of figures of merit should be carefully analyzed; the computational time is a key element to perform UQ in SA; the large number of uncertain input parameters may complicate the interpretation of correlation or sensitivity analysis; there is the need for a statistically solid handling of failed calculations.

RNA N6-methyladenosine modification-based biomarkers for absorbed ionizing radiation dose estimation

Radiation triage and biological dosimetry are critical for the medical management of massive potentially exposed individuals following radiological accidents. Here, we performed a genome-wide screening of radiation-responding mRNAs, whose N6-methyladenosine (m6A) levels showed significant alteration after acute irradiation. The m6A levels of three genes, Ncoa4, Ate1 and Fgf22, in peripheral blood mononuclear cells (PBMCs) of mice showed excellent dose-response relationships and could serve as biomarkers of radiation exposure. Especially, the RNA m6A of Ncoa4 maintained a high level as long as 28 days after irradiation. We demonstrated its responsive specificity to radiation, conservation across the mice, monkeys and humans, and the dose-response relationship in PBMCs from cancer patients receiving radiation therapy. Finally, NOCA4 m6A-based biodosimetric models were constructed for estimating absorbed radiation doses in mice or humans. Collectively, this study demonstrated the potential feasibility of RNA m6A in radiation accidents management and clinical applications.

From Prediction to Prevention: Leveraging Deep Learning in Traffic Accident Prediction Systems

We propose a novel system leveraging deep learning-based methods to predict urban traffic accidents and estimate their severity. The major challenge is the data imbalance problem in traffic accident prediction. The problem is caused by numerous zero values in the dataset due to the rarity of traffic accidents. To address the issue, we propose a grid-clustered feature map with the ideas of grids and cells. To predict the occurrence of accidents in the grid, we introduce an accident detector that combines the power of a Convolutional Neural Network (CNN) with a Deep Neural Network (DNN). Then, hierarchical DNNs are supposed to be an accident risk classifier to estimate the risk of each cell in the accident-occurrence grid. The proposed system can effectively reduce instances with no traffic accidents. Furthermore, we introduce the concept of the Accident Risk Index (ARI) to better represent the severity of risk at each cell. Also, we consider all the explanatory variables, such as dangerous driving behaviors, traffic mobility, and safety facility information, that can be related to traffic accidents. To improve the prediction accuracy, we further take into consideration all the explanatory variables, such as dangerous driving behaviors, traffic mobility, and safety facility information, that can be related to traffic accidents. In the experiment, we highlight the benefits of our method for urban traffic accident management by significantly improving model performance compared to the baselines. The feasibility and applicability of the proposed system are validated in the data of Daejeon City, Republic of Korea. The proposed prediction system can dynamically advise and recommend commuters, traffic management systems, and city planners on alternatives, optimizations, and interventions.

Case studies on radioactivity and decay heat contribution from coating materials of irradiated accident tolerant fuel for a typical PHWR

Seven coating materials such as Al2O3, NbC, Si, SiC, TiN, Y2O3, and ZrC have been considered as a possible coating material towards development of accident tolerant fuel for a typical pressurized heavy water reactor. For an effective severe accident management strategy in addition to spent fuel handling, storage and transport, it is required to know the contribution to the radioactivity burden and decay heat load from the irradiated coating materials of accident tolerant fuel. Under irradiation of coating material in PHWR flux condition, the decay chain of each activated radionuclide has been simulated using ISOGEN code using one group homogenized point cross section. In this paper, radioactivity and decay heat contributions from different irradiated coating materials have been quantified and compared. The minimum contribution to radioactivity and decay heat is observed in SiC after irradiation of 445 days of normal operation. Out of all the coating materials considered in the study, most radioactivity and decay heat were added due to irradiation of coating materials Y2O3. From reactivity load, source term, and decay heat perspectives, silicon-based coating materials are found to be the most suitable.

Assessment of CATHARE code against DEC-A upper head SBLOCA experiments

Design Extension Conditions (DEC)-A assessments of the operating nuclear power plants are generally considered for the purpose of getting additional safety demonstrations of their capability to undergo conditions that are generally more severe than DBAs by features implemented in the design and accident management measures. The pursued methodology is generally based upon Best Estimate approaches aiming at verifying that the safety limits in terms of integrity of the barriers against eventual large or early releases of radioactive material are fulfilled. These aspects are nowadays being experimentally and analytically addressed within the OECD/NEA experimental projects like the ATLAS and PKL series where a set of DEC-A experiments are considered. In this paper, experiments related to SBLOCA at the vessel upper head of the pressurized vessel of ATLAS and PKL are analytically assessed using the CATHARE code. These experiments includes issues related to common cause failure of the safety injection system and operator actions for preventing core excessive overheating. It is shown that, on the one hand, the safety features embedded in the design together with the operator actions are capable to prevent the progression towards a severe accident state and on the other hand, the code prediction capabilities for such scenario are generally good but still to be enhanced.

The Relationship Between Resilience and Conflict Management Styles from the Perspective of the Prehospital Emergency Medicine Operational Staff: A Cross-sectional Descriptive Study

Background: The numerous pre-hospital emergency medicine operational staff interactions with different people cause many conflicts. In addition to affecting their physical and mental health, these conflicts lead to severe problems for the health of society and patients. Objectives: This study aimed to determine the relationship between resilience and conflict management styles from the perspective of pre-hospital emergency medicine operational staff of the Medical Emergency and Accident Management Center in Golestan Province in 2022. Methods: This descriptive correlational study recruited 200 operational staff working in the pre-hospital emergency center in Golestan Province. They were selected using a stratified sampling method with proportional allocation. The data were collected using a demographic questionnaire, the Connor-Davidson Resilience Scale (CD-RISC), and the Rahim Organizational Conflict Inventory-II (ROCI-II). Results: Pearson correlation results demonstrated a direct and significant relationship between resilience and conflict management styles (P = 0.011, r = 0.180); the resilience score increased with an increase in the score of conflict management styles. In addition, resilience was directly associated with compromising (P = 0.012, r = 0.178) and integrating styles (P = 0.001, r = 0.276). Finally, a direct and significant relationship existed between job interest and resilience (P = 0.01). The linear regression analysis showed a significant relationship between the resilience score and the score of conflict management styles (β = 0.17). Conclusions: Resilience can improve the conflict management styles of pre-hospital emergency medicine operational staff. Moreover, job interest can enhance resilience, indirectly affecting conflict management. Pre-hospital emergency managers and officials should hold resilience training courses for pre-hospital emergency operatives.

ELSMOR – towards European Licensing of Small Modular Reactors: Methodology recommendations for light-water small modular reactors safety assessment

Decarbonization of energy production is key in today’s societies and nuclear energy holds an essential place in this prospect. Besides heavy-duty electricity production, other industrial and communal needs could be served by integrating novel nuclear energy production systems, among which are low-power nuclear devices, like small modular reactors (SMRs). The ELSMOR (towards European Licensing of Small Modular Reactors) European project addresses this topic as an answer to the Horizon 2020 Euratom NFRP-2018-3 call. The consortium includes 15 partners from eight European countries, involving research institutes, major European nuclear companies and technical support organizations. The 3.5-year project, launched in September 2019, investigates selected safety features of light-water (LW) SMRs with focus on licensing aspects. Providing a comprehensive compliance framework that regulators can adopt and operate, the licensing process of such SMRs could be optimized, helping their deployment. In this prospect, as a result of ELSMOR’s work, this article gives an overview of the specific issues that LW-SMRs may bring about in the different domains of nuclear safety, in terms of: Methodological standpoints: safety goals, safety requirements, safety principles (defence-in-depth implementation);Main safety functions of reactivity control, decay heat removal and confinement management;Severe accident management;Other safety issues particular to SMRs: use of shared systems; performing of multi-unit probabilistic safety assessment (PSA); refuelling, spent fuel management, transport and disposal management. In this article, adequate methodologies are developed to deal with these issues and to help assess the safety of LW-SMRs. This work gives a precious synthesis of the safety assessment issues of LW-SMRs and of the associated methodologies developed in the context of the ELSMOR European project.

In-depth investigation of natural convection thermal characteristics of BALI experiment through Eulerian computational fluid dynamics code and comparison with Lagrangian code

In-vessel retention through external reactor vessel cooling (IVR-ERVC) is a severe accident management (SAM) strategy that has been adopted and used in many nuclear reactors such as AP1000, APR1400, and light water reactor etc. Some reactor accidents have raised concerns about nuclear reactors among residents, leading to a decrease in residents' acceptability and many studies on SAM are being conducted. Experiments on IVR-ERVC are almost impossible due to its specificity, so fluid characteristics are analyzed through BALI experiments with similar condition. In this study, computational fluid dynamics (CFD) via Reynolds-averaged Navier-Stokes (RANS) and large eddy simulation (LES) for BALI experiments were performed. Steady-state CFD analysis was performed on three turbulence models, and SST k-ω model was in good agreement with the experimental measurement temperature within the maximum error range of 1.9%. LES CFD analysis was performed based on the RANS analysis results and it was confirmed that the temperature and wall heat flux for depth was consistent within an error range of 1.0% with BALI experiment. The LES CFD analysis results were compared with those of the Lagrangian-based solver. LES matched the temperature distribution better than SOPHIA, but SOPHIA calculated the position of boundary between stratified layer and convective layer more accurately. On the other hand, Lagrangian-based solver predicted several small eddy behaviors of the convective layer and LES predicted large vortex behavior. The vibration characteristics near the cooling part of the BALI experimental device were confirmed through Fast Fourier Transform (FFT) investigation. It was found that the power spectral density for pressure at least 10 times higher near the side cooling than near the top cooling.

Construction and application of knowledge graph for grid dispatch fault handling based on pre-trained model

With the construction of new power systems, the power grid has become extremely large, with an increasing proportion of new energy and AC/DC hybrid connections. The dynamic characteristics and fault patterns of the power grid are complex; additionally, power grid control is difficult, operation risks are high, and the task of fault handling is arduous. Traditional power-grid fault handling relies primarily on human experience. The difference in and lack of knowledge reserve of control personnel restrict the accuracy and timeliness of fault handling. Therefore, this mode of operation is no longer suitable for the requirements of new systems. Based on the multi-source heterogeneous data of power grid dispatch, this paper proposes a joint entity–relationship extraction method for power-grid dispatch fault processing based on a pre-trained model, constructs a knowledge graph of power-grid dispatch fault processing and designs, and develops a fault-processing auxiliary decision-making system based on the knowledge graph. It was applied to study a provincial dispatch control center, and it effectively improved the accident processing ability and intelligent level of accident management and control of the power grid.

Implications of homocysteine levels and carotid intima-media thickness in Indian stroke patients

Background The study aimed to evaluate the role of homocysteine (HCY) in modulating various stroke parameters. The primary objective was to study the correlation of HCY levels with carotid intima-media thickness (IMT) in stroke patients and investigate if HCY levels had any predictive value for the National Institutes of Health Stroke Scale (NIHSS) score. Material and Methods Seventy-eight patients of magnetic resonance imaging or computed tomography scans-confirmed acute ischaemic stroke were recruited for this study, and the NIHSS score was evaluated upon admission. Fasting blood samples were tested for serum HCY, fasting blood glucose (FBG) and lipid profile. Ultrasonography of the neck ascertained IMT of common carotid artery (CCA) and internal carotid artery (ICA). Results The mean age of male and female subjects was 57.88±13.97 and 59.16±13.62 years, respectively. 71.93% of stroke patients were hyperhomocysteinemic (HHcyc), and 24.36% were hyperlipidemic. Patients with NIHSS ≥5 had higher LDL cholesterol than those with NIHSS <5. Positive correlations were found between FBG and CCA IMT and triglyceride and NIHSS. HCY cut off of ≥15 μmol/L had 91.7% sensitivity and 66.7% specificity for predicting NIHSS ≥15. HHcyc state was associated with increased ICA IMT. HHcyc state was best predicted by ICA IMT and HCY positively correlated with ICA IMT. Conclusions HHcyc state holds a good predictive value for the severity of stroke. We also concluded that ICA IMT measurement may reduce the need for a HCY test as it predicts higher HCY levels, reducing the burden on resources. We suggest that evaluating HCY and ICA IMT should be part of the standard cerebrovascular accident management protocol.

Evaluating the effectiveness of machine learning techniques in forecasting the severity of traffic accidents

Traffic accidents pose a significant public safety concern, leading to numerous injuries and fatalities worldwide. Predicting the severity of these accidents is crucial for developing effective road safety measures and reducing casualties. This paper proposes an analytic framework that utilizes machine learning models, including Naive Bayes, Random Forest, Logistic Regression, and Artificial Neural Networks, to predict the severity of traffic accidents based on contributing factors. This study analyzed ten years of UK traffic accident data (2005–2014, N = 2,047,256) to develop and compare different ML models. Results show that the proposed Random Forest and Logistic Regression models achieved an 87% overall prediction accuracy, outperforming Naive Bayes (80%) and Artificial Neural Networks (80%). By employing Random Forest-based feature importance analysis, the study identified Engine Capacity, Age of the vehicle, make of vehicle, Age of the driver, vehicle manoeuvre, daytime, and 1st road class as the most sensitive variables influencing traffic accident severity prediction. Additionally, the suggested RF model outperformed most existing models, attaining a remarkable overall accuracy and superior predictive performance across various injury severity classes. The findings have significant implications for developing efficient road safety measures and enhancing the current traffic safety system. The proposed framework and models can be adapted to various datasets to achieve accurate and effective predictions of traffic accident severity, serving as a valuable reference for implementing traffic accident management and control measures. Future research could extend the proposed framework to datasets containing Casualty Accident information to further improve the accuracy of injury severity prediction.

Critical heat flux model for heated horizontally oriented cylindrical vessel and its application to PHWR calandria under severe accident scenario

In-vessel retention (IVR) of molten corium is a key severe accident management strategy adopted in pressurized heavy water reactors (PHWRs) and is recognised as the only option to manage a complete core melt scenario. Since the PHWR calandria vessel is completely surrounded by a large pool of water, the vessel itself is expected to act as a ‘core catcher’. The success of IVR strategy depends up on whether the actual heat flux imparted by molten corium is less than the critical heat flux (CHF). In the present work, a hydrodynamics model is developed and applied to obtain the variation of CHF along outer surface of 220 and 700 MWe Indian PHWR calandria vessel and tube. The thermal margin available for success of IVR strategy is evaluated. The governing equations for external buoyancy driven boundary layer flow are derived and solved in non-dimensional form. The details of the mathematical model, benchmarking exercises, validation aspects and application of the model to PHWR calandria vessel and tube are discussed. Parametric studies are presented to bring out the influence of diameter, system pressure, subcooling of water, depth of submergence and slip ratio on the variation of CHF along the cylindrical vessel surface.

Numerical simulation technologies for safety evaluation in plant lifecycle optimization method, ARKADIA for advanced reactors

This paper describes the development of Advanced Reactor Knowledge- and AI-aided Design Integration Approach through the whole plant lifecycle (ARKADIA) which provides best possible solutions for the design, safety measures, maintenance, and decommissioning of advanced nuclear reactors. ARKADIA consists of state-of-the-art numerical simulation methods, the artificial intelligence technologies, and a knowledge base that includes experiences from the development and operation of the fast reactors and the related research and development. Two subsystems of ARKADIA: ARKADIA-Design and ARKADIA-Safety, are currently being developed individually as the first target of sodium-cooled fast reactors. In a subsequent development phase, the two subsystems will be integrated into a single system, ARKADIA, that is applicable to advanced reactors with a variety of concepts, coolants, configurations, and output levels. ARKADIA-Design offers the functions to support design optimization both in normal operating conditions and design basis events mainly during a conceptual design stage in the fields of core design, plant structure design including thermal-hydraulics analysis, and maintenance plan optimization. The main technology of ARKADIA-Design is based on the multi-level simulation approach by the coupled analysis with numerical analysis codes according to the user’s requirements. For instance, the coupled simulation of neutronics, core deformation, and core thermal hydraulics could evaluate the negative feedback effect of the core deformation reactivity during the plant transient. ARKADIA-Safety is developed for the automatic optimization of severe accident management and their feedback to a plant design. ARKADIA-Safety includes the thermal-hydraulics and multi-physics code, SPECTRA, for in- and ex-vessel integrated severe accident simulation. The basic capability to evaluate severe accident progress was demonstrated through the analysis of a hypothetical loss of reactor level event in a sodium-cooled fast reactor.

Measurement of the water-vapor void fraction in a 4x4 unheated rod bundle

ABSTRACT In recent years, computational fluid dynamics (CFD) simulations have been used to evaluate the two-phase flow behavior inside fuel bundles for nuclear core design and accident management. Space – time distributions of the void fraction and interfacial velocity in bundle systems at high temperatures and pressures are important for validating CFD codes describing two-phase flow. However, such space – time distributions of the void fraction and interfacial velocity in bundle systems are difficult to obtain under high-temperature and high-pressure conditions. Thus far, we have developed an experimental apparatus with a 4 × 4 unheated rod bundle by adapting a through-rod wire mesh sensor to measure the void fraction and interfacial velocity distributions under high pressures and high temperatures. In this study, we measured distributions of the void fraction and interfacial velocity in a water–vapor system under high-pressure conditions up to 2.6 MPa and high temperatures, using the developed apparatus. We demonstrate that the experimental apparatus yields reasonable results for two-phase flow inside a fuel bundle. However, the analysis method used in this study could not properly estimate the interfacial velocity under some experimental conditions, highlighting the need to improve the method for analysis of the interfacial velocity.

Use of supporting software tool for decision-making during low-probability severe accident management at nuclear power plants

In the project NARSIS – New Approach to Reactor Safety ImprovementS – possible advances in safety assessment of nuclear power plants (NPPs) were considered, which also included possible improvements in the field of management of low probability accident scenarios. As a part of it, a supporting software tool for making decisions under severe accident management was developed.
 The mentioned tool, named Severa, is a prototype demonstration-level decision supporting system, aimed for the use by the technical support center (TSC) while managing a severe accident, or for the training purposes. Severa interprets, stores and monitors key physical measurements during accident sequence progression. It assesses the current state of physical barriers: core, reactor coolant system, reactor pressure vessel and containment. The tool gives predictions regarding accident progression in the case that no action is taken by the TSC. It provides a list of possible recovery strategies and courses of action. The applicability and feasibility of possible action courses in the given situation are addressed. For each action course, Severa assesses consequences in terms of probability of the containment failure and estimated time window for failure. At the end, Severa evaluates and ranks the feasible actions, providing recommendations for the TSC. The verification and validation of Severa has been performed in the project and is also described in this paper. Although largely simplified in its current state, Severa successfully demonstrated its potential for supporting accident management and pointed toward the next steps needed with regard to further advancements in this field.

OPTIMIZATION OF ROAD SAFETY PARTNERSHIP ACTION (RSPA) IN HANDLING TRAFFIC PROBLEMS IN THE JURISDICTION OF THE TANJUNG PRIOK PORT POLICE STATION

The Tanjung Priok Port in Indonesia faces challenges in traffic management and road safety. To address these issues, the Tanjung Priok Port Police Traffic Unit has implemented Road Safety Partnership Action (RSPA) activities. This study aims to determine the implementation of Road Safety Partnership Action (RSPA) activities carried out by the Tanjung Priok Port Police Traffic Unit in handling traffic problems in the Tanjung Priok Port area. The study incorporates various theories, including Rosen's cooperation theory, Terry's management theory (including planning, organizing, implementing, and supervising), Dr. E Mulyana's competency theory, and problem-solving theory. A qualitative approach with descriptive analysis was employed. The findings revealed suboptimal implementation of the RSPA activities by the Tanjung Priok Port Police Traffic Unit in addressing traffic and road transportation issues. Furthermore, the competence of the Satlantas Polres Pelabuhan Tanjung Priok personnel in executing the RSPA activities was also deemed suboptimal. The active system and methodology employed in the RSPA activities have not been fully maximized. Therefore, optimization measures are required, including strengthening coordination and communication capabilities, empowering budget support and improving facilities and infrastructure in RSPA activities, enhancing the enforcement of traffic violations and management of traffic accidents, fostering personnel quality in executing the RSPA activities, implementing traffic engineering measures in anticipation of increased port activities related to transportation, encouraging community participation, and utilizing advancements in information technology, particularly in traffic engineering within the Tanjung Priok Port area.

PKP-PK Unit Personnel Strategy Analysis in Mitigating Aircraft Accidents at Adi Soemarmo Boyolali International Airport

This study aims to find out how well and how hard the Aviation Accident Assistance and Fire Fighting (PKP-PK) personnel handle fires at Adi Soemarmo Boyolali International Airport. This research will help by facilitating PKP-PK to follow the safety SOP (Standard Operation Procedure) if an incident occurs. Case study method descriptive qualitative research was used for this study. The PKP-PK unit at Adi Soemarmo Boyolali International Airport was used as a research location. The results of the review show how the progress and progress of the Avionics Accident Management and Fire Fighting (PKP-PK) workforce in tackling fire incidents at the Adi Soemarmo Boyolali World Air Terminal. PKP-PK personnel always carry out their responsibilities in accordance with applicable regulations.

Accident/RTO/Abandoned Vehicle Investigation Using QR Code on Vehicle

Abstract: In India fatal road traffic accidents constitute a significant public health problem in many countries around the world. In Saudi Arabia, road accidents are one of the leading causes of death. The delay in detecting and caring for people who have been exposed to traffic accidents increases the risk of injuries. Injury care after the accident is severely affected by time; a few minutes may separate life from death. Several solutions have been proposed to reduce the incidence of accidents or to reduce the mortality rate at a high financial cost. Recent approaches are using built-in vehicle accident notification system. While these approaches work in pleasing manner, they are expensive, maintenance complex task, and are not available in all cars. However, there is a lack of methods and solutions used to detect the rapid occurrence of accidents and thus speed in transfer of patients to medical centres. In this project we are providing solution for betterment of traffic accident management The various uses we are providing are vehicle identification, in case of accident to identify the victim in case of vehicle stolen-using chasse number, etc. we are using QR code to make the users documents secure. QR Codes have fast response time and have large storage capacity, QR Codes can be used perfectly to send encrypted data (messages) to the receiver. In user panel, user will upload documents after submission the verification takes place in verification panel then the verified user will be given the unique QR code. At the signal, traffic police will scan the QR code and get all the documents of the respective user. So this system will provide a smart and easy way of verification of documents and identifying the user in accident management system

Comparison of random forest and support vector machine regression models for forecasting road accidents

One of the world’s concerns today is the rate of road traffic accidents (RTA). The overwhelming majority of these accidents occur in low and middle-income countries. RTA are one of the leading causes of death in Rwanda. RTA prediction is crucial for both transportation management and intelligent transportation systems (ITS) development. This paper adopted the use of two modelling techniques, Random forest (RF) and Support vector machine (SVM) for short-term road accident forecasting. The data used to evaluate the models was obtained from the Police. The lower error indices of MAE, MSE, RMSE and higher coefficient of determination (R2) were accuracy measures in comparing the models. The RF model performed better than the SVM model as it revealed higher R2=0.91 compared to the SVM model that was with R2=0.86. Machine learning methods are promising tools for the prediction of road accidents. Prediction positively influences safety enhancements and regulation formulation to prevent future accidents. The appropriate prediction method would help policymakers and healthcare providers adjust their contributions to the accident management process.