Crash Models Research Articles

Prognostic Models in Severe Traumatic Brain Injury: A Systematic Review and Meta-analysis.

This review aimed to analyze the results of investigations that performed external validation or that compared prognostic models to identify the models and their variations that showed the best performance in predicting mortality, survival, and unfavorable outcome after severe traumatic brain injury. Pubmed, Embase, Scopus, Web of Science, Cumulative Index to Nursing and Allied Health Literature, Google Scholar, TROVE, and Open Grey databases were searched. A total of 1616 studies were identified and screened, and 15 studies were subsequently included for analysis after applying the selection criteria. The Corticosteroid Randomization After Significant Head Injury (CRASH) and International Mission for Prognosis and Analysis of Clinical Trials in Traumatic Brain Injury (IMPACT) models were the most externally validated among studies of severe traumatic brain injury. The results of the review showed that most publications encountered an area under the curve ≥ 0.70. The area under the curve meta-analysis showed similarity between the CRASH and IMPACT models and their variations for predicting mortality and unfavorable outcomes. Calibration results showed that the variations of CRASH and IMPACT models demonstrated adequate calibration in most studies for both outcomes, but without a clear indication of uncertainties in the evaluations of these models. Based on the results of this meta-analysis, the choice of prognostic models for clinical application may depend on the availability of predictors, characteristics of the population, and trauma care services.

Finite mixture Negative Binomial-Lindley for modeling heterogeneous crash data with many zero observations

Crash data are often highly dispersed; it may also include a large amount of zero observations or have a long tail. The traditional Negative Binomial (NB) model cannot model these data properly. To overcome this issue, the Negative Binomial-Lindley (NB-L) model has been proposed as an alternative to the NB to analyze data with these characteristics. Research studies have shown that the NB-L model provides a superior performance compared to the NB when data include numerous zero observations or have a long tail. In addition, crash data are often collected from sites with different spatial or temporal characteristics. Therefore, it is not unusual to assume that crash data are drawn from multiple subpopulations. Finite mixture models are powerful tools that can be used to account for underlying subpopulations and capture the population heterogeneity. This research documents the derivations and characteristics of the Finite mixture NB-L model (FMNB-L) to analyze data generated from heterogeneous subpopulations with many zero observations and a long tail. We demonstrated the application of the model to identify subpopulations with a simulation study. We then used the FMNB-L model to estimate statistical models for Texas four-lane freeway crashes. These data have unique characteristics; it is highly dispersed, have many locations with very large number of crashes, as well as significant number of locations with zero crash. We used multiple goodness-of-fit metrics to compare the FMNB-L model with the NB, NB-L, and the finite mixture NB models. The FMNB-L identified two subpopulations in datasets. The results show a significantly better fit by the FMNB-L compared to other analyzed models.

Intelligent Nanoscopic Cyclist Crash Modelling for Variable Environmental Conditions

A cyclist is a vulnerable road user whose interaction with the road infrastructure depends on several factors, including variable environmental conditions of lighting and meteorological road surface. This paper is concerned with nanoscopic crash modelling under the riskiest environmental conditions. There are very few works in the literature dealing with such modelling. An intelligent methodological framework consisting of the data collection unit and a knowledge processing unit (KPU) is proposed. In the knowledge processing unit, a combination of a) Statistical, b) Data learning and c) Casual inference methods are applied for investigating crashes on the study area of Tyne and Wear county in North-East of England. Three predictive nanoscopic road safety models are constructed (with 86% accuracy) using a) Spatial, b) Personal, and c) Infrastructure input variables. The importance of each of the identified input variable is estimated by deep learning and statistically validated through chi-square test and Cramer’s <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$V$ </tex-math></inline-formula> statistic. It is found that unsafeness of interaction between rider and infrastructure depends on lighting and road surface meteorological conditions. Different environmental conditions present a varying degree of risk to different types of infrastructure. The riskiest environment conditions are significantly affected by rider’s gender and age, traffic flow regime, specific riding manoeuvre, and the road hierarchy difference. The increase in the number of variables, a rider encounters during his entire trip, imparts risky riding behaviour, affecting its safe interaction with the infrastructure. A novel infrastructure variable, i.e. ‘functional road hierarchy level and direction’ introduced in this work, is found to be a critical road safety variable. A shift in road safety analysis towards nanoscopic modelling can help achieve zero-vision road traffic fatality. The study reinforces the need to plan and design infrastructure to move towards a more holistic approach while considering this vulnerable road user’s limitations.

Machine learning based real-time prediction of freeway crash risk using crowdsourced probe vehicle data

Real-time prediction of crash risk can support traffic incident management by generating critical information for practitioners to allocate resources for responding to anticipated traffic crashes proactively. Unlike previous studies using archived traffic data covering a limited highway environment such as a segment or corridor, this study uses a statewide live traffic database from HERE to develop real-time traffic crash prediction models. This database provides crowdsourced probe vehicle data that are high-resolution real-time traffic speed for the entire freeway network (nearly 2,000 miles) in Alabama. This study aims to use machine learning models to predict crash risk on freeways according to pre-crash traffic dynamics (e.g., mean speed, speed reduction) along with static freeway attributes. Traffic speed characteristics were extracted from the HERE database for both pre-crash and crash-free traffic conditions. Random Forest (RF), Support Vector Machine (SVM) and Extreme Gradient Boosting (XGBoost) were developed and compared. Separate models were estimated for three major crash types: single-vehicle, rear-end, and sideswipe crashes. The model prediction accuracy indicated that the RF models outperform other models. Models for rear-end crashes are found to have greater accuracy than other models, which implies that rear-end crashes have a significant relationship with pre-crash traffic dynamics and are more predictable. The traffic speed factors that are ranked high in terms of feature importance are the speed variance and speed reduction prior to crashes. According to partial dependence plots, the rear-end crash risk is positively related to the speed variance and speed reductions. More results are discussed in the paper.

FE Crash Modeling of Aluminum-FRP Hybrid Components Manufactured by a Hybrid Forming Process

Through the patented process of hybrid forming [1], it is possible to produce a bonded metal-plastic-hybrid component in one process step with the help of an edge-sealed pressing tool. Such a component exhibits an enormous energy absorption potential. To use this complete potential, a reliable FE-Modelling is necessary, that can exactly replicate the complex material layup consisting of an isotropic metal, a very thin bonding layer, and an anisotropic glass mat reinforced thermoplastic (GMT) for crash load case. A methodology is proposed to numerically predict the behavior of the metal GMT aluminum components. And finally, the experimental results of Hybrid components are validated for three-point bending and axial crash load cases.

Did Operating Speeds During COVID-19 Result in More Fatal and Injury Crashes on Urban Freeways?

Impacts of the COVID-19 pandemic in the transportation arena included less traffic, higher speeds, and higher fatal and injury crash frequencies. Many news media reported on speeding and its impact. However, the majority of these reporting are based on partial or incomplete information. The current study aims to understand the association between speed and crash on the freeways of Dallas (Texas) by collecting data from the National Performance Management Research Dataset, the Texas Department of Transportation’s (TxDOT’s) roadway inventory, and TxDOT’s crash database for 2018–2020. The results show decreasing traffic volume, increasing average operating speed, and increasing fatal and severe crash frequencies per 100 million vehicle miles traveled during 2020 (April–November). This study developed 8-month- and daily-level safety prediction models for fatal and injury crashes. The 8-month-level dataset contains speed measures as an aggregate for the 8-month period. The daily-level database includes operating speeds and fatal and injury crashes at the daily level where segments experiencing fatal and injury crashes were temporally matched with the same segment with the same day of the week and with no fatal and injury crash occurrences. For the 8-month models, average operating speed and speed variability are positively associated with fatal and injury crash frequencies during the COVID period. This association was also found for daily-level models. The findings of this study can help transportation agencies in developing strategies (for example, posted speed limit reconsideration, additional enforcement at specific locations) for crash reduction.

Cross-city crash severity analysis with cost-sensitive transfer learning algorithm

Due to the difficulties of data collection in some cities and the relatively small portion of more severe crashes, this paper proposes a cost-sensitive transfer learning framework for more robust crash severity analysis. Specifically, to address the class imbalance issue, cost-sensitive learning method is adopted by assigning unequal cost values to different crash severity levels to obtain unbiased classification results. Moreover, due to the existence of city-irrelevant common crash contributing factors, cross-city crash severity analysis is developed, i.e., transferring common crash severity knowledge from other cities with transfer learning algorithm to assist crash severity modelling in target city that suffers from data scarcity problem. In this study, the crash datasets of Victorian Australia and Seattle are selected as the target and source domains respectively. To address the issue of heterogeneous explanatory features among these two datasets and extract the interpretable common crash severity knowledge, a feature alignment approach is proposed which can represent the cross-city data with unified feature representations on their original explanatory feature spaces. The two proposed models, i.e., cost-sensitive transfer logistic regression (CST-LR) and cost-sensitive transfer support vector machine (CST-SVM), have demonstrated better performance in comparison with twelve commonly used crash severity models, especially when target city crash data is scarce. The most significant crash contributing factors extracted by proposed model also show higher degree of consistency with the true contributing factors obtained from the target dataset, in comparison with the model built without transfer learning. The results could provide policy implications and counter measures for crash severity mitigation.

Small ionic radii limit time step in Martini 3 molecular dynamics simulations.

Among other improvements, the Martini 3 coarse-grained force field provides a more accurate description of the solvation of protein pockets and channels through the consistent use of various bead types and sizes. Here, we show that the representation of Na+ and Cl- ions as "tiny" (TQ5) beads limits the accessible time step to 25fs. By contrast, with Martini 2, time steps of 30-40fs were possible for lipid bilayer systems without proteins. This limitation is relevant for systems that require long equilibration times. We derive a quantitative kinetic model of time-integration instabilities in molecular dynamics (MD) as a function of the time step, ion concentration and mass, system size, and simulation time. We demonstrate that ion-water interactions are the main source of instability at physiological conditions, followed closely by ion-ion interactions. We show that increasing the ionic masses makes it possible to use time steps up to 40fs with minimal impact on static equilibrium properties and dynamical quantities, such as lipid and solvent diffusion coefficients. Increasing the size of the bead representing the ions (and thus changing their hydration) also permits longer time steps. For a soluble protein, we find that increasing the mass of tiny beads also on the protein permits simulations with 30-fs time steps. The use of larger time steps in Martini 3 results in a more efficient exploration of configuration space. The kinetic model of MD simulation crashes can be used to determine the maximum allowed time step upfront for an efficient use of resources and whenever sampling efficiency is critical.

Severity modeling of work zone crashes in New Jersey using machine learning models

In the United States, the probability of work zone crashes has increased due to an increase in renovation works by transportation infrastructures. The severity of work zone crashes is associated with multiple contributing factors such as the roadway’s geometric design features, temporal variables, environmental conditions, types of vehicles, and driver behaviors. For this study, we acquired and analyzed three years (2016–2018) of work zone crash data from the state of New Jersey. We investigated the performance of several machine learning methods, including Support Vector Machine, Random Forest, Catboost, Light GBM, and XGBoost to predict the type of injury severity resulting from work zone crashes. To evaluate models’ performances, some statistical evaluation parameters such as accuracy, precision, and recall scores were calculated. In addition, a sensitivity analysis was conducted to assess the impact of the most influential factors in work zone-related crashes. Random Forest and Catboost outperformed the other models in terms of predicting fatal, major, and minor injuries. According to the sensitivity analysis, crash type and speed limit were the most significantly associated variables with crash severity. The findings of this study are expected to facilitate the identification of appropriate countermeasures for reducing the severity of work zone crashes.

A Machine Learning–Based Prognostic Model for the Prediction of Early Death After Traumatic Brain Injury: Comparison with the Corticosteroid Randomization After Significant Head Injury (CRASH) Model

Machine learning (ML) has been used to predict the outcomes of traumatic brain injury. However, few studies have reported the use of ML models to predict early death. This study aimed to develop ML models for early death prediction and to compare performance with the corticosteroid randomization after significant head injury (CRASH) model. We retrospectively reviewed traumatic brain injury patients between February 2017 and August 2021. The patients were randomly assigned to a training set and a test set. Predictive variables included clinical findings, laboratory values, and computed tomography findings. The ML models (random forest, support vector machine [SVM], logistic regression) were developed with the training set. The CRASH model is a prognostic model that was developed based on 10,008 patients included in the CRASH trial. The ML and CRASH models were applied to the test set to evaluate the performance. A total of 423 patients were included; 317 and 106 patients were randomly assigned to the training and test sets, respectively. The area under the curve was highest in the SVM (0.952, 95% confidence interval= 0.906-0.990) and lowest in the CRASH model (0.942, 95% confidence interval= 0.886-0.999). There were no significant differences between the area under the curves of the ML and CRASH models (P=0.899 for random forest vs. the CRASH model, P=0.760 for SVM vs. the CRASH model, P=0.806 for logistic regression vs. the CRASH model). The ML models may have comparable performances compared to the CRASH model despite being developed with a smaller sample size.

Factors explaining pedestrian-involved fatality crashes on National Highways in India

Pedestrians continue to face high risk of getting involved in fatal and serious injury crashes all over the world. In many high-income countries, pedestrian involvement in fatal crashes occur mostly in urban areas. However, in many low- and middle-income countries in Asia and Africa, pedestrian involvement in fatal crashes occur on intercity highways too. This research analyses fatal pedestrian crash characteristics, and identifies probable contributory factors to pedestrian involvement in fatal crashes using logistic regression for two-, four-, and six-lane National Highways. The fatal pedestrian crash density is found to be the highest at 1.37 crashes/km/year on six-lane divided NH-1. The binary logistic regression estimation results for pedestrian involvement in the fatal crash model revealed that the predictors: “number of lanes” and “time of crash” are found to be significant at 95% level. The model results for the variable “number of lanes” highlights the need to study pedestrian crossing behaviour on highways in detail. The design standards for pedestrian crossing facilities in urban areas may not be suitable for National Highways in particular multi-lane highways. In-depth research is required to understand the suitability of various traffic calming measures and other possible interventions which can ensure pedestrian safety on highways.

Macro-level literature analysis on pedestrian safety: Bibliometric overview, conceptual frames, and trends

Due to the high volume of documents in the pedestrian safety field, the current study conducts a systematic bibliometric analysis on the researches published before October 3, 2021, based on the science-mapping approach. Science mapping enables us to present a broad picture and comprehensive review of a significant number of documents using co-citation, bibliographic coupling, collaboration, and co-word analysis. To this end, a dataset of 6311 pedestrian safety papers was collected from the Web of Science Core Collection database. First, a descriptive analysis was carried out, covering whole yearly publications, most-cited papers, and most-productive authors, as well as sources, affiliations, and countries. In the next steps, science mapping was implemented to clarify the social, intellectual, and conceptual structures of pedestrian-safety research using the VOSviewer and Bibliometrix R-package tools. Remarkably, based on intellectual structure, pedestrian safety demonstrated an association with seven research areas: “Pedestrian crash frequency models”, “Pedestrian injury severity crash models”, “Traffic engineering measures in pedestrians’ safety”, “Global reports around pedestrian accident epidemiology”, “Effect of age and gender on pedestrians’ behavior”, “Distraction of pedestrians”, and “Pedestrian crowd dynamics and evacuation”. Moreover, according to conceptual structure, five major research fronts were found to be relevant, namely “Collision avoidance and intelligent transportation systems (ITS)”, “Epidemiological studies of pedestrian injury and prevention”, “Pedestrian road crossing and behavioral factors”, “Pedestrian flow simulation”, and “Walkable environment and pedestrian safety”. Finally, “autonomous vehicle”, “pedestrian detection”, and “collision avoidance” themes were identified as having the greatest centrality and development degrees in recent years.

Reliability analysis of motorcycle crash severity outcomes: Consideration of model selection uncertainty

Objective While a large amount of work has been conducted on different types of crash injury severity models, model selection uncertainty remains a critical issue in traffic safety research. The objective of this study is to handle model selection uncertainty by combining multiple models. Methods Motorcycle crashes in Michigan from 2010 to 2014 are collected for the analysis. A model averaging approach is used to integrate useful information from three commonly used crash injury severity models: multinomial logit model, ordered logit model, and ordered probit model to deal with the situation where the model selection uncertainty exists in crash data analysis. The ratios of model posterior probabilities between models are used to quantify the model selection uncertainty. In addition, the effectiveness of the method is illustrated by comparing it with the single-best model. Results The ratios of model posterior probabilities among models approximate to 1. It means that three models have the same importance in statistical analysis of motorcycle injury severity, resulting in model selection uncertainty. The comparison between the results of model averaging approach and single-best model shows that the single-best model tends to overestimate the effects of risk factors on motorcycle injury severities because of ignoring the model selection uncertainty; parameter errors and confidence intervals of model averaging are greater and wider than those of the single-best model due to between-model uncertainty included in the model averaging; some risk factors are significant in the model averaging approach while not in the single-best model. Results from model averaging approach reveal that drunk or riding under influence, angle/sideswipe/head on crashes, speed limit of 35 mph or higher, and signal control play significant roles in the motorcycle crashes. Conclusions The study contributes to the existing crash injury-severity literature by developing a model averaging approach to explore the relationship between motorcyclist’s injury-severity and its contributing factors. The model averaging approach overcomes the limitations of the current crash injury-severity modeling approaches by (1) revealing the potential model selection uncertainty among injury-severity models with model posterior probabilities; (2) more reliably accounting for the effects of risk factors on motorcyclist’ injury severities through integrating all information from the candidate models; and (3) better presenting the underlying unreliability of the analysis results from each individual model.

A Structural Design of a Child Seat Based on Morphological Elements and Ergonomics.

In order to improve the safety and comfort of child seat structural design, this paper combines ergonomics and morphological elements to analyze the structural design of child seat and establish a crash model. Moreover, the obtained kinematic response and injury curves are compared with the corresponding actual tested kinematic response and injury parameters to analyze the biomechanics of child occupant injury, the injury characteristics of child occupants in frontal and side collisions, and the evaluation criteria for head, neck, and chest injuries. In addition, this paper combines the intelligent design method to design a safety seat that meets the needs of children. The results show that the structural design method of child seat based on morphological elements and ergonomics proposed in this paper can play an important role in the design of child seat.

Analysis of driver-injury severity: a comparison between speeding and non-speeding driving crash accounting for temporal and unobserved effects

This paper aims to investigate the differences between temporal stability of factors influencing driver-injury severities in crashes involving speeding and non-speeding driving using a six-year (2012–2017) crash data in Thailand. With two possible driver injury severity outcomes (no/minor and severe/fatal), random parameter binary logit models, that allow for heterogeneity in means and variances, were estimated to fully account for unobserved heterogeneities (i.e., allow crash-level factors to vary across crashes and to influence random parameter distribution). While most factors were unstable over time, speeding crash models result showed that stable factors decreasing probability of severe/fatal injury were restraint, van, passenger car, pickup truck, running-off-road on straight and hitting guardrail and mounting traffic island; whereas stable factor increasing probability of severe/fatal injury were central/eastern/southern regions. In non-speeding driving crash model, stable factors decreasing probability of severe/fatal injury were restraint, truck, and running-off-road on straight and hitting guardrail; whereas stable factors increasing probability of severe and fatal injury were under influence of alcohol and van. The findings of this research could potentially be utilized to improve highway safety and facilitate the development of more effective crash injury mitigation policies. Practical-related recommendation based on the results is also provided.

Improving Spatiotemporal Transferability of Real-Time Crash Likelihood Prediction Models Using Transfer-Learning Approaches

A real-time crash likelihood prediction model is an important component of the proactive traffic safety management system. Over the past decades, numerous models have been proposed for predicting real-time crash likelihood and achieved promising results. However, most studies have ignored the model transferability, especially for deep-learning models. The transferability of a model could be defined as applying the model to new data which obtain from different locations or periods. The purpose of this study is to improve the spatiotemporal transferability of a deep-learning crash likelihood prediction model by using transfer-learning approaches. Trajectory and crash data from five arterials in Florida were used in this study. A two-layer long short-term memory (LSTM) model was developed to predict real-time crash likelihood. Two scenarios were created for investigating spatial and temporal transferability of the developed model. Experimental results suggested that the model could be accurately transferred to new data by using the fine-tuning transfer-learning approach. In the framework of this research, the transferred models achieved higher predictive accuracy than models which were directly developed on the new data. Moreover, the spatial transfer learning outperformed the temporal transfer learning in predictive accuracy. For example, when the percentage of test data was 70%, the spatial transferred model had an average area under the curve (AUC) of 0.74. while the temporal transferred model had an average AUC of 0.65. Results from this study could be applied to transfer pretrained crash likelihood prediction models to new locations when few crashes are available.

DETERMINATION OF STIFFNESS AND DAMPING PARAMETERS FROM A VEHICLE MODEL IN A FRONTAL IMPACT INTO THE RIGID BARRIER USING THE MATLAB

The main goal of this paper is to create a computer crash model (up to the level of the double mass-spring-damper model, which is described by a system of two differential equations and where the stiffness and damping coefficients - physical parameters are calculated using the Matlab function Y = solve (eqns) - Equations and systems solver) using measured real data obtained from a frontal impact of a vehicle into a rigid barrier. The vehicle crash modelling process can be performed in two ways. One of them, which is also applied in this article, is based on the System Identification Toolbox, which contains MATLAB® functions, Simulink® blocks and a special application for compiling models of dynamic systems from measured I / O data.

Adaptive surrogates of crashworthiness models for multi-purpose engineering analyses accounting for uncertainty

Uncertainty Quantification (UQ) is a booming discipline for complex computational models based on the analysis of robustness, reliability and credibility. UQ analysis for nonlinear crash models with high dimensional outputs presents important challenges. In crashworthiness, nonlinear structural behaviours with multiple hidden modes require expensive models (18 h for a single run). Surrogate models (metamodels) allow substituting the full order model, introducing a response surface for a reduced training set of numerical experiments. Moreover, uncertain input and large number of degrees of freedom result in high dimensional problems, which derives to a bottle neck that blocks the computational efficiency of the metamodels. Kernel Principal Component Analysis (kPCA) is a multidimensionality reduction technique for non-linear problems, with the advantage of capturing the most relevant information from the response and improving the efficiency of the metamodel. Aiming to compute the minimum number of samples with the full order model. The proposed methodology is tested with a practical industrial problem that arises from the automotive industry.

Safety analytics at a granular level using a Gaussian process modulated renewal model: A case study of the COVID-19 pandemic

With the advance of intelligent transportation system technologies, contributing factors to crashes can be obtained in real time. Analyzing these factors can be critical in improving traffic safety. Despite many crash models having been successfully developed for safety analytics, most models associate crash observations and contributing factors at the aggregate level, resulting in potential information loss. This study proposes an efficient Gaussian process modulated renewal process model for safety analytics that does not suffer from information loss due to data aggregations. The proposed model can infer crash intensities in the continuous-time dimension so that they can be better associated with contributing factors that change over time. Moreover, the model can infer non-homogeneous intensities by relaxing the independent and identically distributed (i.i.d.) exponential assumption of the crash intervals. To demonstrate the validity and advantages of this proposed model, an empirical study examining the impacts of the COVID-19 pandemic on traffic safety at six interstate highway sections is performed. The accuracy of our proposed renewal model is verified by comparing the areas under the curve (AUC) of the inferred crash intensity function with the actual crash counts. Residual box plot shows that our proposed models have lower biases and variances compared with Poisson and Negative binomial models. Counterfactual crash intensities are then predicted conditioned on exogenous variables at the crash time. Time-varying safety impacts such as bimodal, unimodal, and parabolic patterns are observed at the selected highways. The case study shows the proposed model enables safety analytics at a granular level and provides a more detailed insight into the time-varying safety risk in a changing environment.

Understanding Crash Risk Using a Multi-Level Random Parameter Binary Logit Model: Application to Naturalistic Driving Study Data

This study presents a framework to employ naturalistic driving study (NDS) data to understand and predict crash risk at a disaggregate trip level accommodating for the influence of trip characteristics (such as trip distance, trip proportion by speed limit, trip proportion on urban/rural facilities) in addition to the traditional crash factors. Recognizing the rarity of crash occurrence in NDS data, the research employs a matched case-control approach for preparing the estimation sample. The study also conducts an extensive comparison of different case-to-control ratios including 1:4, 1:9, 1:14, 1:19, and 1:29. The model parameters estimated with these control ratios are reasonably similar (except for the constant). Employing the 1:9 sample, a multi-level random parameters binary logit model is estimated where multiple forms of unobserved variables are tested including (a) common unobserved effects for each case-control panel, (b) common unobserved factors affecting the error margin in the trip distance variable, and (c) random effects for all independent variables. The estimated model is calibrated by modifying the constant parameter to generate a population conforming crash risk model. The calibrated model is employed to predict crash risk of trips not considered in model estimation. This study is a proof of concept that NDS data can be used to predict trip-level crash risk and can be used by future researchers to develop crash risk models.