Accident Injury Severity Research Articles

Determinants of driver injury severity in electric vehicle crashes: A random parameters binary probit model with heterogeneity in means and variances

This study aims to investigate the factors significantly affecting occupant injury severity in electric vehicle (EV) accidents, with a particular focus on traffic flow characteristics before accidents, which have often been overlooked in previous research. Using data on EV accidents from January 1, 2021, to December 31, 2021, in Guangdong Province, China, this study considers various vehicle, road, weather, and pre-accident traffic flow characteristics. The research employs the random parameters binary probit model with heterogeneity in means and variances, comparing it with the binary probit model and the random parameters binary probit model to comprehensively address unobserved heterogeneity and further explain the factors contributing to the randomness of random variables. The results indicate that the random parameters binary probit model with heterogeneity in means and variances provides a superior fit. The findings reveal that variables such as the time of day, type of vehicle involved in the collision, color of EV, average morning/evening peak traveling hours significantly impact the severity of injuries in EV accidents. Additionally, the black indicator exhibits heterogeneity in mean and variance during the afternoon period. This study offers an in-depth understanding of the mechanisms behind driver injury severity in EV accidents and contributes to the development of effective countermeasures to protect drivers from severe injuries.

Improving traffic accident severity prediction using MobileNet transfer learning model and SHAP XAI technique.

Traffic accidents remain a leading cause of fatalities, injuries, and significant disruptions on highways. Comprehending the contributing factors to these occurrences is paramount in enhancing safety on road networks. Recent studies have demonstrated the utility of predictive modeling in gaining insights into the factors that precipitate accidents. However, there has been a dearth of focus on explaining the inner workings of complex machine learning and deep learning models and the manner in which various features influence accident prediction models. As a result, there is a risk that these models may be seen as black boxes, and their findings may not be fully trusted by stakeholders. The main objective of this study is to create predictive models using various transfer learning techniques and to provide insights into the most impactful factors using Shapley values. To predict the severity of injuries in accidents, Multilayer Perceptron (MLP), Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Residual Networks (ResNet), EfficientNetB4, InceptionV3, Extreme Inception (Xception), and MobileNet are employed. Among the models, the MobileNet showed the highest results with 98.17% accuracy. Additionally, by understanding how different features affect accident prediction models, researchers can gain a deeper understanding of the factors that contribute to accidents and develop more effective interventions to prevent them.

Incorporating spatio-temporal correlation and interaction into a generalized ordered logit model for examining injury severities of traffic accidents

Spatio-temporal correlation and interaction are significant features of traffic accident data. To account for the spatio-temporal correlation and interaction and the ordinal nature simultaneously, spatio-temporal generalized ordered logit models with different temporal treatments are advocated to examine accident injury severities. In the context of Bayesian inference, we estimate the advocated models and compare them with traditional generalized ordered logit model and spatial generalized ordered logit model using six-year (2014-2019) accident data from the Dongguang section of Guangzhou-Shenzhen Coastal Freeway in China. The results indicate that there are significant spatio-temporal effects and interaction in the accident severity data, and that the spatio-temporal generalized ordered logit models yield low values of deviation information criterion and more reasonable parameter estimates than the generalized ordered logit and spatial generalized ordered logit models do. The estimation results reveal that covariates related to vehicle type, accident type, season, time, horizontal curvature, and bridge have significant effects on accident injury severities. The findings above demonstrate the superiority of the proposed spatio-temporal generalized ordered logit models for predicting accident severities.

Decision trees applied to injury severity in road accidents with only one victim – focus on vulnerable users

The injury severity resulting from a road accident is usually defined based on the most serious victim, which can involve more than one driver, pedestrian, or passenger. Unlike other works that focus on driver characteristics, the present study developed for urban roads focuses on vulnerable users by limiting the database to accidents with a single victim with more serious injuries. Using the CART algorithm, the selected methodology strives to reduce the effects of data imbalance, incorporating various misclassification costs to improve the ‘accident with death’ prediction (minority class) and evaluating the quality results by association rules. After incorporating a 5:1 misclassification cost, recall increased from 0% to 43.3%. Two predictive ‘death’ decision rules were validated, and the identified factors were alcohol/drug consumption, type of accident, age group and annual average daily traffic for traffic above 70 km/h. Limiting the study to accidents with only one person suffering a more serious injury allowed for the identification of significant variables related to vulnerable users, and that can be considered in support of decision-making to reduce the severity of accidents.

Prioritizing rear-end crash explanatory factors for injury severity level using deep learning and global sensitivity analysis

Traffic accidents are usually unique events with unpredictable geographical and temporal dimensions; thus, accident injury severity level (INJ-SL) analysis presents formidable categorization and data stability problems. Classical statistical models are limited in their ability to correctly model INJ-SL, whilst sophisticated machine learning approaches do not appear to have any equations to prioritize/analyze multiple contributing factors to forecast accidents accompanying INJ-SLs. In addition, the intercorrelations between the input variables may render the conclusions of a formal sensitivity analysis incorrectly. Rear-end collisions are the most common form of traffic accidents; consequently, their linked INJ-SL requires more research. This paper provides a complex technique based on a deep learning paradigm paired with different indicators of Global Sensitivity Analysis to address all of these concerns. Unlike existing neural network designs, this technique presents a deep residual neural network structure that employs residual shortcuts (i.e., connections). The connections enable the DRNNs to sidestep a few levels of the deep network architecture, evading the regular training with high accuracy issues. Using the trained DRNNs model, a Latin Hypercube sampling simulation was undertaken to determine each explanatory component's influence on the resulting INJ-SL. The latest available data from 2011 to 2018 is used to assess all rear-end collisions in North Carolina. A comparison was made between the performance of two different schemes of data categorization using a set of global sensitivity metrics. It was determined that the devised technique overcame the data heterogeneity problems to achieve an accuracy of 87%. In addition, the proposed sensitivity analysis identified the most relevant factors associated with INJ-SL rear-end collisions.

Driver's license, head protection devices and severity of motorcyclists' injuries in traffic accidents.

to describe traffic accidents involving motorcyclists and analyze the association between possession of a motorcycle driver's license and use of helmets according to the severity of injuries. a cross-sectional study was conducted among all patients hospitalized in the traumatology and orthopedics sector of a public reference hospital in northeastern Brazil. 170 patients were surveyed, the majority were male (95.9%). Their ages ranged from 18 to 67 years. Most were black or brown (52.3%), had completed elementary school (58.9%) and had monthly income smaller than two minimum wages (56.5%). An association was found between being licensed to drive a motorcycle and wearing a helmet. Among those who suffered moderate injuries, this association was OR=5.66(1.85-17.23) and among those who suffered severe injuries it was OR=13.57(2.82-65.14). people who were licensed to drive motorcycles used a helmet as protective equipment more often and, in accidents, suffered fewer injuries.

Predicting and factor analysis of rider injury severity in two-wheeled motorcycle and vehicle crash accidents based on an interpretable machine learning framework

Objective As one of the vulnerable road users in accidents, how to improve the two-wheeled motorcyclist’s driving safety and reduce accident injury is a public health issue. Accurate identification of the factors influencing the severity of accidents is an important prerequisite for mitigating injury from crashes. Methods Based on a vehicle and a two-wheeled motorcycle crash accident data from the China in-depth accident study database (CIDAS), this study uses the performance evaluation indicators of accuracy, precision, recall, F1-score, AUC, and the ROC curve. The classification and prediction performances of the six machine learning methods on the dataset are compared, and the LightGBM algorithm with the best performance is selected to model the accident injury severity of the motorcyclists. The SHAP method is used to extend the interpretability of the LightGBM model results. Based on the SHAP method, the importance, main effect, and the interaction effect of factors under each accident injury severity are quantitatively analyzed. Results The model prediction accuracy is 92.6%, the F1-Score is 92.8%, and the AUC value is 0.986. The importance of factors varies with the accident injury severity of motorcyclists. The kilometers traveled per year by the driver, the throwing distance of the motorcyclist, and the road speed limit are the three most important factors. The motorcyclist is more likely to suffer fatal injuries when the throwing distance is >1,000 cm. Conclusions The prediction model of driver injury severity based on LightGBM algorithm has a good prediction performance. It can be used to analyze the influence factors of injury severity in two-wheeled motorcyclist accident by combining the model with SHAP method. These results could help the traffic management department to take measures to reduce accident injury of motorcyclists.

Exploring the differences in rider injury severity in vehicle-two-wheelers accidents with dissimilar fault parties

Objective: The division of responsibility in vehicle-two-wheelers accidents reflects the extent to which different fault parties contributed to the occurrence of the accident, with significant differences in the injuries sustained by the riders in accidents where diverse parties were primarily responsible. We want to explore the difference in the severity of injury of riders in different fault parties of accidents so that we can make targeted protection improvements. Methods: In this study, three generalized ordered logit models were established for the total sample (n = 1204), the sample with drivers as the primary fault party (n = 607), and the sample with riders as the primary fault party (n = 597), respectively, to explore the differential impact factors on rider injury severity in vehicle-two-wheelers accidents involving different fault parties. Inter-group difference tests were conducted on the mean rider injury severity caused by differential factors in different accidents. Combining the impact effect trends and mean differences in the model, the differences in rider injury severity in accidents involving different fault parties were analyzed from the standpoints of human, vehicle, and road factors. Results: It was found that the effects of curve on injury severity was sheerly opposite in accidents with different fault parties and that factors, such as visual obstruction, road surface condition, gender, and helmet wearing differed in their effects on rider injury severity under different fault parties accidents. This reveals the driving tendencies and states of both parties in different environments. Conclusion: Based on the differential impact factor analysis and rider injury characteristics in accidents involving different fault parties, suggestions for improvement were made from the perspectives of road facilities, and safety awareness of drivers and riders, which are beneficial for improving rider safety and providing a theoretical reference for future regulations on liability allocation.

Comparison of injury severity between E-bikes-related and other two-wheelers-related accidents: Based on an accident dataset

This study aims to compare the accident injury severity of e-bikes with that of other types of two-wheelers based on accident data and to analyze the factors influencing them. Using 1015 police accident records from Zhangjiakou City in 2020 and 2021, the accident injury severity of e-bikes was firstly compared with that of other two-wheelers based on five levels of accident injury severity classified according to the records. Two ordered Probit regression models were secondly used to compare the factors influencing the accident injury severity of e-bikes with that of other two-wheelers and the magnitude of their effects. At the same time, the contributions of each influential factor to the degree of accident injury of two-wheelers were estimated with the assistance of classification trees. Results show that e-bikes are closer to bicycles than motorcycles in terms of injury severities and the factors influencing them, in which the factors “accident configuration,” “division of responsibility for the accident,” and “collision with a heavy vehicle or four-wheeled vehicle” are significant. Based on the findings, potential measures are suggested to reduce e-bike accident casualties, such as improving rider education, ensuring speed limit enforcement, promoting safety equipment wearing, and making road design friendly to non-motorized and elderly riders. The results of this study can provide an essential reference for traffic management and rider education measures on e-bikes.

Analysis of Motorcycle Accident Injury Severity and Performance Comparison of Machine Learning Algorithms

Motorcycle road traffic accidents represent a big concern, as vulnerable road users account for more than half of all road deaths worldwide. The estimation of the influential factors associated with the increase of injury severity of motorcyclists involved in a road accident is of extreme importance as it provides a necessary basis for the development of an appropriate and targeted sustainable prevention plan for improving road safety. This study adopted the decision tree, ordered logistic regression (LR), random forest (RF), gradient boosting, extreme gradient boosting, k-nearest neighbor, and support vector machine methods to predict the injury severity outcome of motorcycle accidents. All the developed models were compared with six different performance metrics. A 10-year (2010–2019) dataset with motorcycle accidents that occurred in Portugal was used for analysis. As usual in traffic accidents datasets, this dataset is class unbalanced which was dealt with by under-sampling. The developed models made it possible to determine the factors associated with the increase of injury severity of motorcyclists involved in road accidents. The interpretation of each factor is based on the Shapley additive explanations values. The RF and LR models (developed with the balanced dataset) outperformed the other models. Risk factors associated with alcohol consumption, road type, road conditions, location, motorcycle age, rider’s gender, and when the accident occurs were estimated. This study provides a suitable framework analysis to build a proper predictive model, allowing researchers and practitioners to evaluate more accurately the risk factors of motorcycle injury severity.

Lessons learned? Increasing injury severity of electric-scooter accidents over a period of one year: a monocentric follow-up study at a level 1 trauma center

PurposeAfter major COVID-19 lockdown measures were suspended in 2021, E-scooter mobility regrew rapidly. In the meantime, multiple studies were published on the potential risks for e-scooter drivers and the necessity for wearing protective equipment. But did the drivers learn their lessons?MethodsWe observed data of E-scooter-related accidents admitted to the emergency department of a level 1 German trauma center in the year 2021 and compared the data with our previous report (July 2019-July 2020).ResultsN = 97 E-scooter-related accidents were included, marking a 50% increase when compared to the previous observation. Most patients were young adults (28.18 ± 1.13 years) with a notable shift towards a male population (25 vs. 63, p = 0.007). While the injury pattern remained unchanged, injury severity, reflected by a significant increase in shock room treatments (p = 0.005), hospital admissions (p = 0.45), and ICU admissions (p = 0.028), increased. Lastly, we report a higher injury severity of patients driving under the influence of alcohol, expressed by significant differences in hospital admissions, shock room treatments, ICU admissions, intracerebral bleeding (p < 0.0001), and injuries requiring surgery (p = 0.0017).ConclusionThe increase in injury severity and especially the substantial number of accidents due to driving under the influence of alcohol, are alarming for both trauma- and neurosurgeons. As the controversy surrounding the general use of E-scooters will continue, we urge representatives to intensify their efforts regarding prevention campaigns focusing on the potential dangers of E-scooters, especially when driving under the influence of alcohol.

Comparison of traffic accident injury severity prediction models with explainable machine learning

ABSTRACT Traffic accidents are still the main cause of fatalities, injuries and significant delays in highways. Understanding the accident contributing factor is imperative to increase safety in a traffic network. Recent research confirms that predictive modeling is an important tool to comprehend accident contributing factors. However, little effort has been put forward to explain complex machine learning models and their feature effects in accident prediction models. Thus, this study aims to build predictive models based on different machine learning methods and tries to explain the most contributing factors by using Shapley values which was developed based on game theory. Decision Trees, Neural Networks with Multilayer Perceptron (MLP), Support Vector Classifier, Case-Based Reasoning and Naive Bayes Classifier were used to predict the injury severity in accidents. Belt usage, alcohol consumption and speed violations were found as the most effective features and MLP gave the highest accuracy among all the applied predictive models.

Exploring injury severity of Non-Motor vehicle riders involving in traffic accidents using the generalized ordered logit model

This study aims to explore potential factors that affect non-motor vehicles (NMV) riders’ injury severity in accidents with motor vehicles (MV). Factors including human characteristics, vehicles, road features and environmental conditions were investigated. Police-reported crash data from the period of 2007 to 2017 in Xi’an, China were used to develop the generalized ordered logit models. Model results revealed that NMV riders’ injury severity was significantly influenced by rider’s Hukou, type of NMV, type of roadside protection, road structure, linearity, weather, accident time, light condition and visibility level. Besides, factors involving NMV rider’s age, compulsory third party insurance, type of MV, season, road type will increase their risk of suffering from serious/fatal injuries. Research findings are beneficial in helping policymakers to develop measures to improve NMV riders’ safety in China, such as isolating NMV and MV, educating drivers especially those from rural areas, and improving road and environment conditions.

Human Risk Factors for Severity of Injuries in Urban and Suburban Traffic Accidents in Southern Iran: An Insight from Police Data

Background: Globally, transport injuries persist as the leading preventable cause of adolescent harm. Objectives: This study aimed to determine the role of human factors in causing traffic accidents in urban and suburban areas of Jahrom, Fars province, Iran. Materials and Methods: This descriptive study used the recording data of 598 accidents and incidents on urban and suburban roads recorded in the accident registration forms (KAM) of the Police Information and Communication Technology (ICT- FAVA) system in Jahrom in 2020. The obtained data were analyzed by SPSS 20 software using descriptive statistics, chi-square test, and multivariable logistic regression. Simultaneously, population-attributable risks for violations of drivers involved in accidents on urban and suburban roads were determined. Results: The multivariable logistic regression analysis identified sudden diversion (OR = 11.02, 95% CI: 3.79 - 32.00), inattention to the front (OR = 6.68, 95% CI: 3.27 - 13.61), non-observance of the right of priority (OR = 6.25, 95% CI: 2.80 - 13.98), and inability to control the vehicle (OR = 4.05, 95% CI: 1.81 - 8.90) as risk factors for death or injury in urban roads. Meanwhile, death or injury on suburban roads was associated with failure to yield to the right of way (OR = 2.25, 95% CI: 1.08 - 4.67), inattention to the front (OR = 1.95, 95% CI: 1.08 - 3.51), and inability to control the vehicle (OR = 41.86, 95% CI: 1.001 - 4.63). Among humans factors of accidents on urban and suburban roads, inattention to the front (78.84% vs. 37.73%) and failure to yield to the right of way (62.75% vs. 32.31%) had the greatest population-attributable fraction risk factors of death or injury. Conclusions: Inattention to the front and non-observance of the right of way by drivers were the first and second ranks in accidents leading to injury and death. It is suggested that the relevant laws and legislations be intensified and enforced more seriously.

Analysis of the Elderly Pedestrian Injury Severity in Urban Traffic Accidents in Spain using Machine Learning Techniques

Analysis of the Elderly Pedestrian Injury Severity in Urban Traffic Accidents in Spain using Machine Learning Techniques

Analyzing the impact of curve and slope on multi-vehicle truck crash severity on mountainous freeways

Many studies examine the road characteristics that impact the severity of truck crash accidents. However, some only analyze the effect of curves or slopes separately, ignoring their combination. Therefore, there are nine types of the combination of curve and slope in this study. The combination of curve and slope factor that affected the injury severity of truck crashes on mountainous freeways was examined using a correlated random parameter logit model. This method is applied to evaluate the correlation between the random parameters and those that exhibit unobserved heterogeneity. Also, the multinomial logit model and traditional random parameter logit model are used. The study’s data were collected from multi-vehicle truck crashes on mountainous freeways in China. The results showed that the correlated random parameters logit model was better than the others. In addition, they demonstrated a correlation between the random parameters. Based on the estimation coefficients and marginal effects, the combination of curve and slope has a great influence on the injury severity of truck crashes. The main finding is that curve with medium radius and medium slope will significantly increase the probability of medium severity comparing to curve with high radius and flat slope. On the other hand, the injury severity of truck accidents was significantly impacted by crash type, vehicle type, surface condition, time of day, season, lighting condition, pavement type, and guardrail. Variables such as sideswipe, head-on, medium trucks, morning, dawn or dusk and summertime reduced the probability of truck crashes. Rollover, winter, gravel, and guardrail variables increased the risk of truck crashes. Correlations were also discovered between a rollover and dry surface condition and rollover and gravel pavement type. The research findings will help traffic officials determine effective countermeasures to decrease the severity of truck crashes on mountainous freeways.

Orman sertifikasyonunun odun hammaddesi üretim faaliyetlerine etkilerinin incelenmesi (Bolu Orman İşletme Müdürlüğü örneği)

Bu çalışmanın amacı, orman yönetim sertifikasının (OYS) odun hammaddesi üretimine etkilerini teknik ve çevresel açılardan araştırmak, sertifikasyon öncesi ve sonrası üretim işlerinin durumunu incelemektir. Çalışma alanı, 2013 yılında OYS alınmasına yönelik çalışmaların başlanarak 2014 yılı ortalarında tamamlandığı Bolu Orman İşletme Müdürlüğü (OİM)’dür. Çalışmada teknik elemanlar (29 kişi) ve orman üretim işçileri (21 kişi) ile gönüllülük esasına göre yüz yüze görüşme yöntemi ve anket tekniği kullanılarak veriler elde edilmiştir. Anket formları 5’li Likert ölçeğinde olup, katılımcıların temel bilgilerini ve OYS kapsamında teknik personelin ve orman işçilerinin OYS hakkındaki genel ve odun üretimi ile ilgili görüşlerini ortaya koymayı amaçlamaktadır. Anket sonuçlarına göre; OYS kapsamında üretim işçilerine verilen ilkyardım, temel iş sağlığı ve güvenliği eğitimlerinin sonuçlarının işçiler tarafından olumlu algılandığı ve konunun önemsendiği ortaya çıkmıştır. Üretim işçilerine sağlanan kişisel koruyucu donanımların orman alanlarında kesim ve diğer üretim faaliyetleri esnasında yaşanan iş kazalarında yaralanma şiddetlerini azalttığı belirlenmiştir. Ayrıca eğitimlerin sadece doğanın korunması için değil, üretimde çalışanların da bilgilendirilmesi için yapıldığı belirlenmiştir.

Risk prediction and factor analysis of rider’s injury severity in passenger car and E-bike accidents based on interpretable machine learning

Casualties and property losses caused by the passenger car and electric bicycle crash accidents increased year by year. Assessment of the relevant risk factors of injury severity in passenger car and electric bicycle crashes could help to mitigate crash severity. This study uses an emerging machine learning method to predict the relationship between the risk factors and bicyclist accident injury severity in passenger car-electric bicycle collision accidents. The model’s performance is compared and evaluated based on accuracy, precision, recall, F1-Score, area under curve (AUC), and receiver operating characteristic curve (ROC). An interpretable machine learning framework Shapley additive explanations (SHAP) is used to further analyze the relationship between risk factors and bicyclist injury severity. It is found that we can adopt the light gradient boosting machine (LightGBM) algorithm after hyper-parameter optimization to get the highest accuracy (94.85%), precision (95.2%), recall (94.9%), F1-Score (95%), and AUC (0.993) based on the accident data of electric bicycles and passenger cars in the China in-depth accident study dataset from 2014 to 2018. The model can be used to assess new accident cases based on the model learning rate. There are some new findings in the aspects of bicyclists’ physical factors and electric vehicle characteristics. The throwing distance of the bicyclist has a positive impact on the injury severity. The bicyclist is more likely to suffer more serious injuries in a crash accident when the bicyclist is male, or shorter. Electric bicycles have a smaller handlebar width. In general, the lower handlebar height is, or lower saddle height is, the more serious the bicyclist’s injury is. Safety training for drivers can help reduce the injury severity in crash accidents and improve traffic safety.

Analysis of the injury-severity outcomes of maritime accidents using a zero-inflated ordered probit model

This study provides an empirical analysis of the injury severity outcomes of maritime accidents by exploring the influential factors for two underlying injury severity states: the injury-free state and the injury-prone state. The former may reflect the generation mechanism of accidents with limited potential to result in injury outcomes, whereas, the latter may represent injury severity when the accident falls into the injury-prone category. To account for the possible presence of these two underlying regimes, a zero-inflated ordered probit (ZIOP) model is employed using injury-severity data extracted from 1,128 maritime accident investigation reports between 2000 and 2019. The results indicate that on one hand, capsizing/sinking, hull/machinery damage and other accident type, adverse sea state, poor education background and short period of holding the present rank are more likely to be injury-prone. On the other hand, gross tonnage and water depth, distance from the coast, flag state of convenience, and accident type impact the likelihood of severe injuries if the accident is in the injury-prone category. The marginal effect analysis highlights some interesting effects caused by sea state, ship manning and gross tonnage, as well as accident type and location. The results of Akaike's information criteria (AIC), Bayesian information criteria (BIC) and Vuong's test show that the ZIOP model outperforms the traditional ordered probit model and can serve as an alternative to study the injury severity of maritime accidents.

Accident Severity Prediction using Machine Learning

Traffic accidents are among the most critical issues facing the world as they cause many deaths, injuries, and fatalities as well as economic losses every year. Accurate models to predict the traffic accident severity is a critical task for transportation systems. This investigation effort establishes models to select a set of influential factors and to build up a model for classifying the severity of injuries. These models are formulated by various machine learning techniques. Supervised machine learning algorithms and unsupervised machine learning algorithms are implemented on traffic accident data. The major objective is to discover the correlation between different types of the traffic accidents with the type of the injuries. The findings of this study indicate that the unsupervised learning techniques can be a promising tool for predicting the injury severity of traffic accidents.