Search

Single and multi-vehicle (SMV) crashes remain a significant issue, causing serious safety and economic concerns, and therefore deserve more attention. Using crash data in the Beijing-Shanghai and Changchun-Shenzhen freeways over the five years (2015–2019), this paper explored the transferability and heterogeneity for crash type (single-vehicle versus multi-vehicle crashes) and spatiotemporal stability of determinants affecting the injury severity. The random parameters logit approach with heterogeneity in means and variances was used to model three possible crash injury severity outcomes (measured by the most severely injured individual in the crash) of no injury, minor injury, and severe injury and identify the determinants in terms of driver, vehicle, roadway, environment, temporal, spatial, traffic, and crash characteristics. Remarkable differences were observed in the SMV crashes, and the contributing factors also reported considerable temporal and (or) spatial instabilities. The insights of this study should be valuable to help freeway designers and decision-makers understand the contributing mechanism of the factors and develop the proper management strategies and enforcement countermeasures. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

There has been a concerning rise in pedestrian fatalities resulting from traffic accidents. This study conducts an in-depth analysis of the factors that contribute to the injury severity of pedestrians considering human, vehicle, roadway, and environmental characteristics of the crashes. A novel approach is proposed by combing a data mining technique and mixed logit models. First, the Apriori algorithm is employed to uncover patterns between fatal and incapacitating injury outcomes and their influencing factors. Then, mixed logit models are developed to investigate heterogeneity across all observations under two different lighting conditions. It is found that eight variables show heterogeneity affecting the injury severity of crash outcomes. Results also indicate that drivers older than 65 years old will increase the probability of pedestrian injury severity at dark-unlighted roads. Additionally, the present of signal and double yellow line has could increase the injury severity. Creating optimal lighting conditions at pedestrian crossings during nighttime hours and enhancing safety education initiatives for pedestrians are critical factors to improve pedestrian safety. The finding of this study will benefit policymakers and road safety professionals develop more effective strategies for preventing pedestrian injuries in vehicle crashes. [ABSTRACT FROM AUTHOR]

This study explores the temporal instability and non-transferability of the determinants affecting injury severities of pedestrians struck by motorcycles and non-motorcycles. Using the pedestrian-vehicle crash data in Rawalpindi, Pakistan, over three years (2017–2019), three possible crash injury severity categories (minor injury, severe injury, and fatal injury) are estimated using alternative models to account for unobserved heterogeneity. These are a random-parameters multinomial logit (RP-ML) model with heterogeneity in means and variances and a latent-class multinomial logit (LC-ML) model with class probability functions. Temporal instability and non-transferability in the effects of explanatory variables are confirmed using a series of likelihood ratio tests based on the two alternative models. Various variables are observed to determine pedestrian-injury severities, and the estimation results show significant temporal instability and non-transferability in both RP-ML and LC-ML models. However, several explanatory variables produce relatively temporally stable and transferable effects, providing valuable insights to implement effective countermeasures from a long-term perspective. Moreover, out-of-sample predictions are simulated to confirm the temporal instability and non-transferability. At the same time, the LC-ML models produce higher differences for temporal instability and lower differences for non-transferability compared to the RP-ML model. Understanding and depth comparing the estimation results, likelihood ratio tests, and out-of-sample predictions using alternative models is a promising direction for future research to explore how the observed and unobserved heterogeneity can be estimated in terms of temporal instability and non-transferability. [ABSTRACT FROM AUTHOR]

Two-vehicle crashes resulting from distracted driving led to a higher number of fatalities and serious injuries over time. This study utilized machine learning and econometric models to investigate two-vehicle-involved distracted driving crashes from the Crash Report Sampling System within the United States. XGBoost and Random Forest were utilized to identify the top variables based on SHAP value, although mixed logit with unobserved heterogeneity was used to model injury severity. The model results indicate that there is a complex interaction of driver characteristics, such as demographics (male drivers), driver actions (careless driving, driving more than the speed limit of more than 15 mph, hitting a stopped vehicle), a driver without violation history, turning violation, drinking, roadway characteristics (non-interstate highways, undivided and divided roadways with positive barrier, curved roadways, dry surface), environmental conditions (rainy weather), vehicle attributes (motorcycle, displacement volume up to 2500 cc, newer vehicle within five years of crash-involvement), temporal characteristics (4–6 PM, July–September, and year 2017). These findings underscore the importance of driving behavior and roadway design. As such, prioritizing efforts to address distracted driving behavior through driver training and law enforcement, as well as considering its implications for roadway design and maintenance, becomes crucial. [ABSTRACT FROM AUTHOR]

• A comprehensive, explainable accident-data-based AI artifact design is presented. • Utilize aggregate SHAP scores to classify crash data into high-level causal factors. • A systems-level taxonomy of driver behaviors linked to injury severity is discussed. • Separating explanation from models yields managerial insights. Automobile traffic accidents represent a significant threat to global public safety, resulting in numerous injuries and fatalities annually. This paper introduces a comprehensive, explainable artificial intelligence (XAI) artifact design, integrating accident data for utilization by diverse stakeholders and decision-makers. It proposes responsible, explanatory, and interpretable models with a systems-level taxonomy categorizing aspects of driver-related behaviors associated with varying injury severity levels, thereby contributing theoretically to explainable analytics. In the initial phase, we employed various advanced techniques such as data missing at random (MAR) with Bayesian dynamic conditional imputation for addressing missing records, synthetic minority oversampling technique for data imbalance issues, and categorical boosting (CatBoost) combined with SHapley Additive exPlanations (SHAP) for determining and analyzing the importance and dependence of risk factors on injury severity. Additionally, exploratory feature analysis was conducted to uncover hidden spatiotemporal elements influencing traffic accidents and injury severity levels. We developed several predictive models in the second phase, including eXtreme Gradient Boosting (XGBoost), random forest (RF), deep neural networks (DNN), and fine-tuned parameters. Using the SHAP approach, we employed model-agnostic interpretation techniques to separate explanations from models. In the final phase, we provided an analysis and summary of the system-level taxonomy across feature categories. This involved classifying crash data into high-level causal factors using aggregate SHAP scores, illustrating how each risk factor contributes to different injury severity levels. [ABSTRACT FROM AUTHOR]

This research study examined the factors contributing to the injury severity of alcohol-impaired motorcyclists (BAC ≥ 0.08), compared to non-alcohol-impaired motorcyclists (BAC < 0.08). This study modelled rider injury severity in single-motorcycle crashes using random parameter multinomial logit with heterogeneity in mean and variance. This approach accounts for possible unobserved heterogeneity in the data resulting from rider, roadway, motorcycle, traffic and/or environmental conditions. The model results show that rider characteristics, such as role (rider), demographics (age between 50 and 65 years), motorcycle type (cruiser), rider endorsement (endorsement required), riding behaviour (speed more than 10 mph over the speed limit), riding action (no distraction prior to crashes), no helmet usage, roadway characteristics (left curved alignment, road surface condition), temporal characteristics (Sundays), spatial characteristics (Florida Department of Transportation District 5) and crash characteristics (collision with roadside fixed object) interact in a complex way to affect riders' injury severity. The estimated model results suggest that the likelihood of fatality was 3.1 times higher for harmful events of roadside fixed objects, 6.6 times higher for left-aligned roadway and 10.4 times higher for riders in single-motorcycle crashes involving alcohol-impairment (BAC ≥ 0.08) relative to non-alcohol impairment (BAC < 0.08). The results clearly indicate the elevated safety concerns of alcohol impairment beyond the legal limit (BAC ≥ 0.08) has on rider injury severities. Alcohol-impaired riding and its impact on risky riding behaviours needs to be prioritised and addressed through education, enforcement and engineering countermeasures. [ABSTRACT FROM AUTHOR]

Background: Two-tier trauma team activation (TTA)—protocols often fail to safely identify severely injured patients. A possible amendment to existing triage scores could be the measurement of serum lactate. The aim of this study was to determine the ability of the combination of serum lactate and age to predict severe injuries (ISS > 15). Methods: We conducted a retrospective cohort study in a single level one trauma center in a 20 months study-period and analyzed every trauma team activation (TTA) due to the mechanism of injury (MOI). Primary endpoint was the correlation between serum lactate (and age) and ISS and mortality. The validity of lactate (LAC) and lactate contingent on age (LAC + AGE) were assessed using the area under the curve (AUC) of the receiver operating characteristics (ROC) curve. We used a logistic regression model to predict the probability of an ISS > 15. Results: During the study period we included 325 patients, 75 met exclusion criteria. Mean age was 43 years (Min.: 11, Max.: 90, SD: 18.7) with a mean ISS of 8.4 (SD: 8.99). LAC showed a sensitivity of 0.82 with a specificity of 0.62 with an optimal cutoff at 1.72 mmol/l to predict an ISS > 15. The AUC of the ROC for LAC was 0.764 (95% CI: 0.67–0.85). The LAC + AGE model provided a significantly improved predictive value compared to LAC (0.765 vs. 0.828, p < 0.001). Conclusions: The serum lactate concentration is able to predict injury severity. The prognostic value improves significantly taking the patients age into consideration. The combination of serum lactate and age could be a suitable Ad-on to existing two-tier triage protocols to minimize undertriage. Level of evidence: Level IV, retrospective cohort study. [ABSTRACT FROM AUTHOR]

• Machine learning models for crash risk predictions are comprehensively reviewed. • Four staged review: the first three stages summarise existing efforts, and the last stage highlights future research needs. • Critical research needs for crash risk predictions using machine learning models are discussed. • Efficient techniques for data imbalance need to be employed. • Rigorous efforts for data collection and real-time models are required. Accurately modelling crashes, and predicting crash occurrence and associated severities are a prerequisite for devising countermeasures and developing effective road safety management strategies. To this end, crash prediction modelling using machine learning has evolved over two decades. With the advent of big data that provides unprecedented opportunities to better understand the crash mechanism and its determinants, such efforts will likely be accelerated. To gear these efforts, understanding state-of-the-art machine learning-based crash prediction models becomes paramount to summarise the lessons learned from past efforts, which can assist in developing robust and accurate models. This review paper aims to address this gap by systematically reviewing the machine learning studies on crash modelling. Models are reviewed from three aspects of the application: (a) crash occurrence (or real-time crash) prediction, (b) crash frequency prediction, and (c) injury severity prediction. Further, model intricacies that impact model performance are identified and thoroughly reviewed. This comprehensive review highlights specific gaps and future research needs in three aforementioned model applications, such as improper selection of non-crash events for crash occurrence models, the inability of future forecasting of crash frequency models, and inconsistency in injury severity classes. Critical research needs relating to model development, evaluation, and application are also discussed. This review envisages methodological advancements in machine learning models for crash prediction modelling and leveraging big data to better link crashes with its determinants. [ABSTRACT FROM AUTHOR]

This study aimed to explore the factors that affect the severity and number of sports injuries among Korean sports participants in their 20s and 30s. The data of 5118 lifestyle and professional athletes in their 20s and 30s were collected from a sports safety survey conducted by the Korea Sports Safety Foundation in 2019. The characteristics of the study population were analyzed using descriptive analysis. Determinants of injury severity and frequency based on participants' sex were identified using multivariate logistic regression analyses. The results show that among male sports participants, the type of athlete, knowledge of first aids, the physical condition, completing safety education, the skill level, and checking environmental factors were associated with injury severity. Among female sports participants, the type of athlete, the physical condition, performing finishing exercises, completing safety education, and the skill level were associated with injury severity. Additionally, among male sports participants, physical condition, completing safety education, skill level, participating in exercises according to one's fitness level, and having an awareness of accident prevention methods were associated with injury frequency. Lastly, among female sports participants, drinking water during scheduled breaks, carrying water to stay hydrated, physical condition, completing safety education, and skill level were associated with injury frequency. Furthermore, being a lifestyle athlete, being in good physical condition, and having beginner or intermediate skills in one's sport reduced injury severity among Korean sports participants in their 20s and 30s. Being in good physical condition, not completing safety education, and having beginner skills in one's sport reduced the injury frequency among Korean sports participants in their 20s and 30s. These findings suggest that lifestyle and professional athletes should be aware of these factors and participate in sports activities in a manner that reduces injury severity and frequency. Moreover, these factors should be considered when developing strategies to prevent sport injuries in lifestyle and professional athletes and allow them to participate in sports activities safely. [ABSTRACT FROM AUTHOR]

The safety and reliability of undivided two-way highway–rail grade crossings (HRGCs) are of paramount importance in transportation systems. Utilizing crash data from the Federal Railroad Administration between 2020 and 2021, this study aims to predict crash injury severity outcomes and investigate various factors influencing injury severities. The χ2 test was first used to select variables that were significantly associated with injury outcomes. By employing the eXtreme Gradient Boosting (XGBoost) model and interpretable SHapley Additive exPlanations (SHAP), a cross-category safety assessment that offers an evidence-based hierarchy and statistical inference of risk factors associated with crashes, crossings, vehicles, drivers, and environment was provided for killed, injured, and uninjured outcomes. Some significant predictors overlapped between the killed and injured models, such as old driver, driver was in vehicle, main track, went around the gate, adverse crossing surface, and truck, while the other different significant factors revealed that the model could distinguish between different severity levels. Additionally, the results suggested that the model has varying performances in predicting different injury severities, with the killed model having the highest accuracy of 93.36%. The SHAP dependency plots for the top three features also ensure reliable predictions and inform potential interventions aimed at strengthening traffic safety and risk management practices, such as enhanced warning systems and targeted educational campaigns for older drivers. [ABSTRACT FROM AUTHOR]

Climbing, a sport with increasing popularity, poses diverse risks and injury patterns across its various disciplines. This study evaluates the incidence and nature of climbing-related injuries, focusing on how different disciplines and climbers' personal characteristics affect these injuries. Data on injury incidence, severity, and consequences, as well as climbers' personal attributes, were collected through a questionnaire and analyzed using generalized linear models and generalized linear mixed models, Cochran–Armitage tests, and multivariate analysis. Our findings indicate a direct correlation between time spent on bouldering and lead climbing and increased injury frequency, while injury incidence decreases with time in traditional climbing. Interestingly, personal characteristics showed no significant impact on injury incidence or severity. However, distinct patterns emerged in individual disciplines regarding the recent injuries in which age and weight of climbers play a role. While the phase of occurrence and duration of consequences show no significant variation across disciplines, the intensity of the required treatment and causes of injury differ. This research provides insights into climbing injuries' complex nature, highlighting the need for tailored preventive strategies across climbing disciplines. It underscores the necessity for further investigation into the factors contributing to climbing injuries, advocating for more targeted injury prevention and safety measures in this evolving sport. [ABSTRACT FROM AUTHOR]

Traumatic brain injury (TBI) is a major cause of mortality and disability around the world, for which no treatment has been found. Nociceptin/Orphanin FQ (N/OFQ) and the nociceptin opioid peptide (NOP) receptor are rapidly increased in response to fluid percussion, stab injury, and controlled cortical impact (CCI) TBI. TBI-induced upregulation of N/OFQ contributes to cerebrovascular impairment, increased excitotoxicity, and neurobehavioral deficits. Our objective was to identify changes in N/OFQ and NOP receptor peptide, protein, and mRNA relative to the expression of injury markers and extracellular regulated kinase (ERK) 24 h following mild (mTBI) and moderate TBI (ModTBI) in wildtype (WT) and NOP receptor-knockout (KO) rats. N/OFQ was quantified by radioimmunoassay, mRNA expression was assessed using real-time PCR and protein levels were determined by immunoblot analysis. This study revealed increased N/OFQ mRNA and peptide levels in the CSF and ipsilateral tissue of WT, but not KO, rats 24 h post-TBI; NOP receptor mRNA increased after ModTBI. Cofilin-1 activation increased in the brain tissue of WT but not KO rats, ERK activation increased in all rats following ModTBI; no changes in injury marker levels were noted in brain tissue at this time. In conclusion, this study elucidates transcriptional and translational changes in the N/OFQ-NOP receptor system relative to TBI-induced neurological deficits and initiation of signaling cascades that support the investigation of the NOP receptor as a therapeutic target for TBI. [ABSTRACT FROM AUTHOR]

Background: Kiteboarding (kitesurfing on water and snowkiting) is a fairly new sport and is defined as a high-risk sport. The injury rate has been reported to be between 6 and 9 per 1000 h. The aim of the study was to identify and describe kiteboarding-related injuries in Norway over a five-year period. Methods: We used "snowball sampling" to identify kiteboarding accidents in a retrospective study. In addition, we conducted structural searches in the National Air Ambulance Service and Search and Rescue Helicopter patient record databases. All included informants were interviewed. Descriptive methods were used to characterise the sample. Results: Twenty-nine kiteboarders were included, with a total of 33 injuries. One half of the injuries to head, face and neck were cerebral concussions (n = 12). The most common type of injury was bone fractures (n = 28), followed by soft tissue injuries (n = 24). Most injuries were of moderate severity (51%) and falling from less than 5 m was the most common mechanism of injury. Operator error and lack of experience were the most frequently reported causes of accidents (82%). Conclusions: Serious injuries occured during kiteboarding. The majority of kiteboarders reported operator error or lack of experience as the cause of their accident. Prior to kiteboarding, a course highlighting the importance in using helmet for snowkiting and both helmet and life vest in kitesurfing, should be mandatory. [ABSTRACT FROM AUTHOR]

The pedelec 25 (pedal electric cycle) has established itself as a popular mode of transport, with sales rising. Unfortunately, this has also led to an increase in the number of accidents. Analyses of pedelec accidents have been carried out, but most studies are based on technical variables. Neither spatial, geographical factors, for example the terrain, nor socio-geographical aspects, such as whether an accident occurred in a tourist region, have been much addressed. However, geographical exposure can vary significantly. Therefore, we assume that spatial differences contribute to regional variations in numbers of accidents and resulting injuries associated with both bicycle types (pedelecs 25 and conventional). Thus, the aim of this paper is to determine geographical factors that influence severe accidents and to evaluate this influence. We have identified relevant geographical factors and proven their influence on two types of severity: risk of severe bicycle accidents per region (RS) and probability of severe injuries in case of accident (AS). Spatial analyses indicate that for both bicycle types, severity of accident increases in rural, mountainous or tourist regions. Regression analyses of RS provided further evidence: compactness of settlement structure (thus urbanity/rurality), share of tourists, altitude differences (only pedelecs), rate of registered motor vehicles and share of elderly population (only pedelecs) influence the risk of severe bicycle accidents per region. The influence of geographical variables tended to be greater for pedelecs. Regression analyses of AS reveal that geographical factors also have an influence on the probability of severe injuries in case of an accident.