Vehicular crash data used to rank intersections by injury crash frequency and severity.
Ontology highlight
ABSTRACT:
SUBMITTER: Liu Y
PROVIDER: S-EPMC4961217 | biostudies-literature | 2016 Sep
REPOSITORIES: biostudies-literature
Publications
Vehicular crash data used to rank intersections by injury crash frequency and severity.
Liu Yi Y Li Zongzhi Z Liu Jingxian J Patel Harshingar H
Data in brief 20160701
This article contains data on research conducted in "A double standard model for allocating limited emergency medical service vehicle resources ensuring service reliability" (Liu et al., 2016) [1]. The crash counts were sorted out from comprehensive crash records of over one thousand major signalized intersections in the city of Chicago from 2004 to 2010. For each intersection, vehicular crashes were counted by crash severity levels, including fatal, injury Types A, B, and C for major, moderate, ...[more]
Similar Datasets
Project description:BackgroundAdministrative healthcare databases, such as Medicare, are increasingly used to identify groups at risk of a crash. However, they only contain information on crash-related injuries, not all crashes. If the driver characteristics associated with crash and crash-related injury differ, conflating the two may result in ineffective or imprecise policy interventions.MethodsWe linked 10 years (2008-2017) of Medicare claims to New Jersey police crash reports to compare the demographics, clinical diagnoses, and prescription drug dispensings for crash-involved drivers ≥ 68 years with a police-reported crash to those with a claim for a crash-related injury. We calculated standardized mean differences to compare characteristics between groups.ResultsCrash-involved drivers with a Medicare claim for an injury were more likely than those with a police-reported crash to be female (62.4% vs. 51.8%, standardized mean difference [SMD] = 0.30), had more clinical diagnoses including Alzheimer's disease and related dementias (13.0% vs. 9.2%, SMD = 0.20) and rheumatoid arthritis/osteoarthritis (69.5% vs 61.4%, SMD = 0.20), and a higher rate of dispensing for opioids (33.8% vs 27.6%, SMD = 0.18) and antiepileptics (12.9% vs 9.6%, SMD = 0.14) prior to the crash. Despite documented inconsistencies in coding practices, findings were robust when restricted to claims indicating the injured party was the driver or was left unspecified.ConclusionsTo identify effective mechanisms for reducing morbidity and mortality from crashes, researchers should consider augmenting administrative datasets with information from police crash reports, and vice versa. When those data are not available, we caution researchers and policymakers against the tendency to conflate crash and crash-related injury when interpreting their findings.
| S-EPMC11318118 | biostudies-literature
Project description:Predicting crash injury severity is a crucial constituent of reducing the consequences of traffic crashes. This study developed machine learning (ML) models to predict crash injury severity using 15 crash-related parameters. Separate ML models for each cluster were obtained using fuzzy c-means, which enhanced the predicting capability. Finally, four ML models were developed: feed-forward neural networks (FNN), support vector machine (SVM), fuzzy C-means clustering based feed-forward neural network (FNN-FCM), and fuzzy c-means based support vector machine (SVM-FCM). Features that were easily identified with little investigation on crash sites were used as an input so that the trauma center can predict the crash severity level based on the initial information provided from the crash site and prepare accordingly for the treatment of the victims. The input parameters mainly include vehicle attributes and road condition attributes. This study used the crash database of Great Britain for the years 2011-2016. A random sample of crashes representing each year was used considering the same share of severe and non-severe crashes. The models were compared based on injury severity prediction accuracy, sensitivity, precision, and harmonic mean of sensitivity and precision (i.e., F1 score). The SVM-FCM model outperformed the other developed models in terms of accuracy and F1 score in predicting the injury severity level of severe and non-severe crashes. This study concluded that the FCM clustering algorithm enhanced the prediction power of FNN and SVM models.
| S-EPMC7432564 | biostudies-literature
Project description:While the cost of road traffic fatalities in the U.S. surpasses $240 billion a year, the availability of high-resolution datasets allows meticulous investigation of the contributing factors to crash severity. In this paper, the dataset for Trucks Involved in Fatal Accidents in 2010 (TIFA 2010) is utilized to classify the truck-involved crash severity where there exist different issues including missing values, imbalanced classes, and high dimensionality. First, a decision tree-based algorithm, the Synthetic Minority Oversampling Technique (SMOTE), and the Random Forest (RF) feature importance approach are employed for missing value imputation, minority class oversampling, and dimensionality reduction, respectively. Afterward, a variety of classification algorithms, including RF, K-Nearest Neighbors (KNN), Multi-Layer Perceptron (MLP), Gradient-Boosted Decision Trees (GBDT), and Support Vector Machine (SVM) are developed to reveal the influence of the introduced data preprocessing framework on the output quality of ML classifiers. The results show that the GBDT model outperforms all the other competing algorithms for the non-preprocessed crash data based on the G-mean performance measure, but the RF makes the most accurate prediction for the treated dataset. This finding indicates that after the feature selection is conducted to alleviate the computational cost of the machine learning algorithms, bagging (bootstrap aggregating) of decision trees in RF leads to a better model rather than boosting them via GBDT. Besides, the adopted feature importance approach decreases the overall accuracy by only up to 5% in most of the estimated models. Moreover, the worst class recall value of the RF algorithm without prior oversampling is only 34.4% compared to the corresponding value of 90.3% in the up-sampled model which validates the proposed multi-step preprocessing scheme. This study also identifies the temporal and spatial (roadway) attributes, as well as crash characteristics, and Emergency Medical Service (EMS) as the most critical factors in truck crash severity.
| S-EPMC10032500 | biostudies-literature
Project description:AKI increases the risk of developing CKD, but the mechanisms linking AKI to CKD remain unclear. Because proximal tubule injury is the mainstay of AKI, we postulated that proximal tubule injury triggers features of CKD. We generated a novel mouse model to induce proximal tubule-specific adjustable injury by inducing the expression of diphtheria toxin (DT) receptor with variable prevalence in proximal tubules. Administration of high-dose DT in mice expressing the DT receptor consistently caused severe proximal tubule-specific injury associated with interstitial fibrosis and reduction of erythropoietin production. Mild proximal tubule injury from a single injection of low-dose DT triggered reversible fibrosis, whereas repeated mild injuries caused sustained interstitial fibrosis, inflammation, glomerulosclerosis, and atubular glomeruli. DT-induced proximal tubule-specific injury also triggered distal tubule injury. Furthermore, injured tubular cells cocultured with fibroblasts stimulated induction of extracellular matrix and inflammatory genes. These results support the existence of proximal-distal tubule crosstalk and crosstalk between tubular cells and fibroblasts. Overall, our data provide evidence that proximal tubule injury triggers several features of CKD and that the severity and frequency of proximal tubule injury determines the progression to CKD.
| S-EPMC4978049 | biostudies-literature
Project description:To determine whether emergency physicians (EPs) and prehospital emergency medical services (EMS) personnel differ in their assessment of motor vehicle crash (MVC) severity and the potential for serious injury when viewing crash scene photographs.Attending and resident EPs, paramedics, and emergency medical technicians (EMTs) from a single emergency medicine system used a web-based survey platform to rate the severity of 100 crash photographs on a 10-point Likert scale (Crash Score) and the potential for serious injury on a 0-100% scale (Injury Score). Serious injury was defined as skull fracture or intracranial bleeding, spine fracture or spinal cord injury, intrathoracic or intraabdominal injury, or long bone fracture. Crash and Injury Scores were stratified into EP and paramedic/EMT (EMS) groups and the mean score was calculated for each photo. Spearman rank correlation coefficients with 95% confidence intervals (95% CI) and Bland-Altman plots were constructed to assess agreement. Secondary analyses were performed after categorizing data into quartiles based on participants' estimations of MVC severity.A total of 54 attending and 53 resident EPs, 156 paramedics, and 34 EMTs were invited to participate in the survey. Of these, 39 (72%) attending and 46 (87%) resident EPs, 107 (69%) paramedics, and 17 (50%) EMTs completed the survey. A total of 183 (88%) surveys were completed in full. The overall Crash Score correlation coefficient between EPs and EMS was 0.98 (95% CI, 0.97-0.99). The Crash Score correlation coefficients for each quartile were 0.86 (0.57-0.97), 0.93 (0.85-0.96), 0.58 (0.16-0.85), and 0.88 (0.66-0.97), respectively. The overall Injury Score correlation coefficient between EPs and EMS was 0.98 (0.88-0.97). The Injury Score correlation coefficients for each quartile were 0.94 (0.48-0.91), 0.76 (0.50-0.92), 0.80 (0.69-1.00), and 0.94 (0.57-0.97), respectively.Although overall agreement between EPs and EMS personnel was excellent, differences in estimation of crash severity and potential for injury were identified among crashes estimated to be moderate in severity.
| S-EPMC4915374 | biostudies-literature
Project description:Road crash fatality is a universal problem of the transportation system. A massive death toll caused annually due to road crash incidents, and among them, vulnerable road users (VRU) are endangered with high crash severity. This paper focuses on employing machine learning-based classification approaches for modelling injury severity of vulnerable road users-pedestrian, bicyclist, and motorcyclist. Specifically, this study aims to analyse critical features associated with different VRU groups-for pedestrian, bicyclist, motorcyclist and all VRU groups together. The critical factor of crash severity outcomes for these VRU groups is estimated in identifying the similarities and differences across different important features associated with different VRU groups. The crash data for the study is sourced from the state of Queensland in Australia for the years 2013 through 2019. The supervised machine learning algorithms considered for the empirical analysis includes the K-Nearest Neighbour (KNN), Support Vector Machine (SVM) and Random Forest (RF). In these models, 17 distinct road crash parameters are considered as input features to train models, which originate from road user characteristics, weather and environment, vehicle and driver condition, period, road characteristics and regions, traffic, and speed jurisdiction. These classification models are separately trained and tested for individual and unified VRU to assess crash severity levels. Afterwards, model performances are compared with each other to justify the best classifier where Random Forest classification models for all VRU modes are found to be comparatively robust in test accuracy: (motorcyclist: 72.30%, bicyclist: 64.45%, pedestrian: 67.23%, unified VRU: 68.57%). Based on the Random Forest model, the road crash features are ranked and compared according to their impact on crash severity classification. Furthermore, a model-based partial dependency of each road crash parameters on the severity levels is plotted and compared for each individual and unified VRU. This clarifies the tendency of road crash parameters to vary with different VRU crash severity. Based on the outcome of the comparative analysis, motorcyclists are found to be more likely exposed to higher crash severity, followed by pedestrians and bicyclists.
| S-EPMC8341492 | biostudies-literature
Project description:BackgroundThis study examined the impact of transportation infrastructure at intersection and non-intersection locations on bicycling injury risk.MethodsIn Vancouver and Toronto, we studied adult cyclists who were injured and treated at a hospital emergency department. A case-crossover design compared the infrastructure of injury and control sites within each injured bicyclist's route. Intersection injury sites (N=210) were compared to randomly selected intersection control sites (N=272). Non-intersection injury sites (N=478) were compared to randomly selected non-intersection control sites (N=801).ResultsAt intersections, the types of routes meeting and the intersection design influenced safety. Intersections of two local streets (no demarcated traffic lanes) had approximately one-fifth the risk (adjusted OR 0.19, 95% CI 0.05 to 0.66) of intersections of two major streets (more than two traffic lanes). Motor vehicle speeds less than 30 km/h also reduced risk (adjusted OR 0.52, 95% CI 0.29 to 0.92). Traffic circles (small roundabouts) on local streets increased the risk of these otherwise safe intersections (adjusted OR 7.98, 95% CI 1.79 to 35.6). At non-intersection locations, very low risks were found for cycle tracks (bike lanes physically separated from motor vehicle traffic; adjusted OR 0.05, 95% CI 0.01 to 0.59) and local streets with diverters that reduce motor vehicle traffic (adjusted OR 0.04, 95% CI 0.003 to 0.60). Downhill grades increased risks at both intersections and non-intersections.ConclusionsThese results provide guidance for transportation planners and engineers: at local street intersections, traditional stops are safer than traffic circles, and at non-intersections, cycle tracks alongside major streets and traffic diversion from local streets are safer than no bicycle infrastructure.
| S-EPMC3786647 | biostudies-literature
Project description:Road traffic injuries are one of the primary reasons for death, especially in developing countries like Bangladesh. Safety in land transport is one of the major concerns for road safety authorities and other policymakers. For this reason, contributory factors identification associated with crashes is necessary for reducing road crashes and ensuring transportation safety. This paper presents an analytical approach to identifying significant contributing factors of Bangladesh road crashes by evaluating the road crash data, considering three different severity levels (non-fetal, severe, and extremely severe). Generally, official crash databases are compiled from police-reported crash records. Though the official datasets are focusing on compiling a wide array of attributes, an assorted number of unreported issues can be observed that demands an alternative source of crash data. Therefore, this proposed approach considers compiling crash data from newspapers in Bangladesh which could be complimentary to the official crash database. To conduct the analysis, first, we filtered the useful features from compiled crash data using three popular feature selection techniques: chi-square, Two-way ANOVA, and Regression analysis. Then, we employed three machine learning classifiers: Decision Tree, Random Forest, and Naïve Bayes over the extracted features. A confusion matrix was considered to evaluate the proposed model, including classification accuracy, sensitivity, and specificity. The predictive machine learning model, namely, Random Forest using Label Encoder with chi-square and Two-way ANOVA feature selection process, seems the best option for crash severity prediction that provides high prediction accuracy. The resulting model highlights nine out of fourteen independent features as responsible factors. Significant features associated with crash severities include driver characteristics (gender, license type, seat belts), vehicle characteristics (vehicle type), road characteristics (road surface type, road classification), environmental conditions (day of crash occurred, time of crash), and injury localization. This outcome may contribute to improving traffic safety of Bangladesh.
| S-EPMC9732348 | biostudies-literature
Project description:X-linked hydrocephalus, MASA syndrome and certain forms of X-linked spastic paraplegia and agenesis of corpus callosum are now known to be due to mutations in the gene for the neural cell adhesion molecule L1 (19, 30). As a result, these syndromes have recently been reclassified as CRASH syndrome, an acronym for Corpus callosum hypoplasia, Retardation, Adducted thumbs, Spasticity and Hydrocephalus (8). A comparison of existing case reports with molecular genetic analysis reveals a striking correlation between the type of mutation in the L1CAM gene and the severity of the disease. Mutations that produce truncations in the extracellular domain of the L1 protein are more likely to produce severe hydrocephalus, grave mental retardation or early death than point mutations in the extracellular domain or mutations affecting only the cytoplasmic domain of the protein. While less severe than extracellular truncations, point mutations in the extracellular domain do produce more severe neurologic problems than mutations in just the cytoplasmic domain.
| S-EPMC1563987 | biostudies-literature
Project description:BackgroundThe Oral Impacts on Daily Performances (OIDP) index asks the respondents to indicate both, the frequency and severity of the impact. However, it is not clear if the two scaling methods are correlated, and if using one scale is sufficient. The purpose of the study was to investigate the correlation between frequency and severity rating scales of the OIDP instrument, and whether only one of the rating scales can be used instead of both.MethodsA battery of patient-reported outcome questionnaires were administered to a consecutive sample of adult dental patients from HealthPartners dental clinics in Minnesota (N = 2,115). Only those who responded to any of the OIDP items were included in the analysis for this study (N = 873). We assessed correlations between the frequency and severity scales for all OIDP items, and for the summary scores of the two OIDP response scales. We additionally fit a categorical structural equation model (SEM) (or an item factor analysis model) and examined the correlation between two latent variables (Frequency and Severity).ResultsThe correlation estimates for all OIDP items were greater than 0.50, indicating large correlations between the frequency and severity scores for each OIDP item. The correlation estimate between the two summary scores was 0.85 (95% CI [0.82-0.86]). When we calculated the correlation coefficient using a latent variable model, the value increased to 0.96 (95% CI [0.93-1.00]).ConclusionOur study findings show that OIDP frequency and severity scores are highly correlated, which indicates the use of one scale only. Based on previous evidence, we recommend applying the frequency rating scale only in research and clinical settings.
| S-EPMC8855712 | biostudies-literature