Factors Affecting Single and Multivehicle Motorcycle Crashes: Insights from Day and Night Analysis Using XGBoost-SHAP Algorithm

Mixed logit model-based driver injury severity investigations in single- and multi-vehicle crashes on rural two-lane highways

A Motorcyclist-Injury Severity Analysis: A Comparison of Single-, Two-, and Multi-Vehicle Crashes Using Latent Class Ordered Probit Model

Reducing fatal and serious injuries sustained in traffic crashes on tribal lands is a priority of federal, state, and local agencies in the United States. In the state of Arizona, the proportion of fatal and severe injury crashes on several areas of tribal land are 4.0% higher compared with statewide statistics. There is a need to investigate why higher proportions of fatal and severe injuries are occurring on tribal lands to plan effective countermeasures aimed at improving traffic safety in these areas. This study presents an analysis of factors affecting injury severity in crashes occurring within five tribal reservations in the state of Arizona. Crash data were obtained from the Arizona Department of Transportation, and the analysis included data for 9,597 persons involved in traffic crashes on these tribal lands for the years 2010–2016. An ordered logit model with random parameters was estimated using this data to identify factors significantly associated with severe injury outcomes in the event of a crash on tribal lands. Several person-, vehicle-, roadway-, and environmental-related variables were found to impact injury severity. For instance, alcohol and safety device usage were significantly associated with severity outcomes. The results of this study have the potential to aid transportation agencies effectively plan strategies to reduce traffic crash injuries and fatalities on tribal lands, and potential countermeasures considering the 4Es of traffic safety (engineering, education, enforcement, and emergency medical services) are discussed.

Pedestrian injury severity in motor vehicle crashes: An integrated spatio-temporal modeling approach

The impact of weekday, weekend, and holiday crashes on motorcyclist injury severities: Accounting for temporal influence with unobserved effect and insights from out-of-sample prediction

This study aims to explore factors affecting passenger car and truck driver injury severity in passenger car-truck crashes. Police-reported crash data from 2007 to 2017 in Canada are collected. Two-vehicle crashes involving one truck and one passenger car are extracted for modeling. Different injury severities are not equally represented. To address the data imbalance issue, this study applies four different data imbalance treatment approaches, including over-sampling, under-sampling, a hybrid method, and a cost-sensitive learning method. To test the performances of different classifiers, five classification models are used, including multinomial logistic regression, Naive Bayes, Classification and Regression Tree, support vector machine, and eXtreme Gradient Boosting (XGBoost). In both the passenger car driver and truck driver injury severity analysis, XGBoost combined with cost-sensitive learning generates the best results in terms of G-mean, area under the curve, and overall accuracy. Additionally, the Shapley Additive Explanations (SHAP) approach is adopted to interpret the result of the best-performing model. Most of the explanatory variables have similar effects on passenger car and truck driver fatality risks. Nevertheless, six variables exhibit opposite effects, including the age of the passenger car driver, crash hour, the passenger car age, road surface condition, weather condition and the truck age. Results of this study could provide some valuable insights for improving truck traffic safety. For instance, properly installing traffic control devices could be an effective way to reduce fatality risks in passenger car-truck crashes. Besides, passenger car drivers should be extremely cautious when driving between midnight to 6 am on truck corridors.

There is no reliable estimate of costs incurred by motorcycle crashes. Our objective was to calculate the direct costs of all publicly funded medical care provided to individuals after motorcycle crashes compared with automobile crashes. We conducted a population-based, matched cohort study of adults in Ontario who presented to hospital because of a motorcycle or automobile crash from 2007 through 2013. For each case, we identified 1 control absent a motor vehicle crash during the study period. Direct costs for each case and control were estimated in 2013 Canadian dollars from the payer perspective using methodology that links health care use to individuals over time. We calculated costs attributable to motorcycle and automobile crashes within 2 years using a difference-in-differences approach. We identified 26 831 patients injured in motorcycle crashes and 281 826 injured in automobile crashes. Mean costs attributable to motorcycle and automobile crashes were $5825 and $2995, respectively (p < 0.001). The rate of injury was triple for motorcycle crashes compared with automobile crashes (2194 injured annually/100 000 registered motorcycles v. 718 injured annually/100 000 registered automobiles; incidence rate ratio [IRR] 3.1, 95% confidence interval [CI] 2.8 to 3.3, p < 0.001). Severe injuries, defined as those with an Abbreviated Injury Scale ≥ 3, were 10 times greater (125 severe injuries annually/100 000 registered motorcycles v. 12 severe injuries annually/100 000 registered automobiles; IRR 10.4, 95% CI 8.3 to 13.1, p < 0.001). Considering both the attributable cost and higher rate of injury, we found that each registered motorcycle in Ontario costs the public health care system 6 times the amount of each registered automobile. Medical costs may provide an additional incentive to improve motorcycle safety.

Understanding Motorcycle Crash Severity in Pakistan: Insights from Machine Learning and Interaction Effects

Background: Motorcycle accidents are a major cause of head injuries, and the current study evaluated the beneficial impact and effectiveness of helmet usage among injured motorcycle users. This study has been performed to observe motorcycle collisions within 6 months in Rawalpindi and Abbottabad, Pakistan Objectives: The implications of helmet usage were assessed, and the risk factors for severe injury during motorcycle accidents were identified. Materials and Methods: The impacts of several risk factors on injury severity were calculated using univariate and generalized ordinal logistic regression. Results: The multivariate analysis indicated that riders without a helmet were more likely to experience severe (AOR, 2.216; 95% CI, 2.02 to 10.5) or moderate injury (AOR, 1.215; 95% CI, 0.84 to1.77). Riders who experienced crashes involving multiple vehicles were also significantly more likely to experience severe (AOR, 2.473; 95% CI, 1.0 to 3.93) or moderate injury (AOR, 1.192; 95%CI, 0.08 to 0.41). Thus, compared to helmet users, the odds of severe injury are five times higher among motorcyclists with no helmet use when no other factors were controlled for in the analysis. The adjusted odds of severe injuries maybe 2.2 times higher among the riders without helmets vs. riders with helmets. Conclusion: Helmet use levels, injury type, and crash type were identified as risk factors that significantly influenced the risk of severe or moderate injury. Motorcycle riders can reduce their risk of severe injury by adopting preventive measures (helmet use) and by controlling these factors. Road safety strategies to prevent injuries, casualties, and loss of economic resources may benefit from our study findings and the risk of severe injuries can be reduced by proper implementation of Helmet use laws. Keywords: Use; Motorcycle crash; Traumatic brain injury; Disability; Mortality

Objective Motorcycle crashes often result in severe injuries on roads that affect people’s lives physically, financially, and psychologically. These injuries could be notably harmful to drivers of all age groups. The main objective of this study is to investigate the risk factors contributing to the severity of crash injuries in different age groups. Methods This Objective is achieved by developing accurate machine learning (ML) based prediction models. This research examines the relationship between potential risk factors of motorcycle-associated crashes using (ML) and Shapley Additive explanations (SHAP) technique. The SHAP technique further helped interpreting ML methods for traffic injury severity prediction. It indicates the significant non-linear interactions between dependent and independent variables. The data for this study was collected from the Provincial Emergency Response Service RESCUE 1122 for the Rawalpindi region (Pakistan) over three years (from 2017 to 2020). The Synthetic Minority Oversampling Technique (SMOTE) is employed to balance injury severity classes in the pre-processing phase. Results The results demonstrate that age, gender, posted speed limit, the number of lanes, and month of the year are positively associated with severe and fatal injuries. This research also assesses how the modeling framework varies between the ML and classical statistical methods. The predictive performance of proposed ML models was assessed using several evaluation metrics, and it is found that Catboost outperformed the XGBoost, Random Forest (RF) and Multinomial Logit (MNL) model. Conclusion The findings of this study will assist road users, road safety authorities, stakeholders, policymakers, and decision-makers in obtaining substantial and essential guidance for reducing the severity of crash injuries in Pakistan and other countries with prevailing conditions.

Background: Injury is the fifth leading cause of death in the US, and a large proportion of injury deaths result from Motor Vehicle Crashes (MVCs). Side impact collisions pose high risks of death and serious injury compared to other crash types, both for crashes with other vehicles and single-vehicle crashes with fixed objects, such as utility poles. However, few studies have appropriately compared the propensity for injury of these two types of side impact. Methods: The present study used 10 years of data abstracted from the National Automotive Sampling System Crashworthiness Data System (NASS-CDS) to analyze the risks of polytrauma in side impact crashes for two types of side impacts: pole-like fixed objects and other vehicles. Additionally, ratios comparing the relative risk of nearversus far-side occupants in the two types of crashes were calculated. These risk ratios were developed using a multi-variable general estimating equations (GEE) log-binomial model, with injury severity characterized using the injury severity score (ISS), a measure of the extent of polytrauma. Results & Conclusion: Relative to side impacts with other vehicles, pole-type side impacts are highly associated (RR = 1.53 [95% CI: 1.15, 2.03]) with ISS ≥ 16. After adjusting for other crash characteristics, near-side seating position relative to the side of the vehicle receiving the impact was also associated with a significant increase in risk of polytrauma (RR = 1.82 [95% CI: 1.36, 2.44]). The results of the present study inform vehicle and road design from the perspective of injury prevention. Apostolos Alexandridis! !

Objective The study used data for crashes that occurred on two-lane rural highways in Granada, Spain, over a four-year period (2016–2019). The obtained dataset consisted of 1,291 crashes. The data was used to identify the variables that influence crash injury severity. Methods In this study, a hybrid meta-learning methodology based on Bayesian Networks (BNs) and Random Forest (RF) was used. To the authors’ knowledge, these methods have never been combined in a single analysis. BNs identified the main factors influencing crash injury severity and the categories of these factors that are most important for each injury severity. These factors were ranked in importance from highest to lowest using RF. Results It was found that the following variables significantly increase the risk of a fatality in a traffic crash: driver age, crash type, time of day, main crash cause according to police assessment, and lane width. In addition, it was found that the following categories of these factors were associated with a higher risk of fatality: driver age over 45, rollover crash type, nighttime lighting conditions, police reported driver distractions, and lane width of less than 3.25 meters. Conclusion It became evident that using a hybrid meta-learning methodology based on BNs and RF was helpful in identifying the most significant factors, which influence the negative outcome of crashes. Local criteria that may evaluate the traffic safety of present and future highways should be developed and put into use in order to improve the level of traffic safety in two-lane rural highways, reducing the severity of injuries caused by traffic crashes and improving traffic safety.

Children after motor vehicle crashes: Restraint utilization and injury severity

A better understanding of injury severity risk factors is fundamental to improving crash prediction and effective implementation of appropriate mitigation strategies. Traditional statistical models widely used in this regard have predefined correlation and intrinsic assumptions, which, if flouted, may yield biased predictions. The present study investigates the possibility of using the eXtreme Gradient Boosting (XGBoost) model compared with few traditional machine learning algorithms (logistic regression, random forest, and decision tree) for crash injury severity analysis. The data used in this study was obtained from the traffic safety department, ministry of transport (MOT) at Riyadh, KSA, and contains 13,546 motor vehicle collisions along 15 rural highways reported between January 2017 to December 2019. Empirical results obtained using k-fold (k = 10) for various performance metrics showed that the XGBoost technique outperformed other models in terms of the collective predictive performance as well as injury severity individual class accuracies. XGBoost feature importance analysis indicated that collision type, weather status, road surface conditions, on-site damage type, lighting conditions, and vehicle type are the few sensitive variables in predicting the crash injury severity outcome. Finally, a comparative analysis of XGBoost based on different performance statistics showed that our model outperformed most previous studies.

Investigation of pulmonary contusion extent and its correlation to crash, occupant, and injury characteristics in motor vehicle crashes