Epigenetic characterization of sarcopenia-associated genes based on machine learning and network screening

To screen characteristic genes related to sarcopenia by bioinformatics and machine learning, and to verify the accuracy of characteristic genes in the diagnosis of sarcopenia. Download myopia-related data sets from geo public database, find the differential genes through R language limma package after merging, STRING database to build protein interaction network, and do Go analysis and GSEA analysis to understand the functions and molecular signal pathways that may be affected by the differential genes. Further screen the characteristic genes through LASSO and SVM-RFE machine algorithms, make the ROC curve of the characteristic genes, and obtain the AUC value. 10 differential genes were obtained from the data set, including 7 upregulated genes and 3 downregulated genes. Eight characteristic genes were screened by a machine learning algorithm, and the AUC value of characteristic genes exceeded 0.7. In patients with sarcopenia, the expression of TPPP3, C1QA, LGR5, MYH8, and CDKN1A genes are upregulated, and the expression of SLC38A1, SERPINA5, and HOXB2 genes are downregulated. The above genes have high accuracy in the diagnosis of sarcopenia. The research results provide new ideas for the diagnosis and mechanism research of sarcopenia.

Comparison of corridor-level fatal and injury crash models with site-level models for network screening purposes on Florida urban and suburban divided arterials

Objective: Develop corridor-level network screening models to identify high-risk corridors where safety improvements could be implemented to reduce fatal and injury (FI) crashes. Methods: A novel corridor definition focused on context classification and lane count was developed and applied to urban and suburban four-lane divided arterial roadways in Florida. Negative binomial regression models were developed for multi- and single-vehicle crashes using 80% of the corridors (training set). Crash frequency predictions were obtained from the developed corridor models and similar site-level models from the Highway Safety Manual (HSM) models for the remaining 20% of the corridors (testing set). Results from all models were adjusted using the empirical Bayes (EB) method. Results: A total of 130 corridors were identified across seven counties. These corridors contained approximately 349 km (217 miles) of roadway and experienced 11,437 multi-vehicle and 746 single-vehicle crashes that resulted in fatalities or injuries from 2017 to 2021. After applying the HSM site-level models and the developed corridor-level models to the testing set (both with and without EB adjustments), the corridor-level models with EB adjustments were the most accurate for corridor crash prediction. Applying the corridor-level models with EB adjustments to the testing set gave a predicted value of 386.44 crashes/year, which was the closest to the observed crash frequency of 383.20 crashes/year. From the corridor-level models, a 3.48-km (2.16-mile) high-risk corridor in Miami-Dade County was identified and analyzed site-by-site using the HSM methodology to identify specific sites within the corridor where safety improvements could provide the most FI crash reductions. Conclusions: The corridor-level models were more accurate and statistically reliable than similar HSM models while being less data intensive. They also only required corridor-level data rather than data for each intersection and segment. By using readily available data, the methods in this paper can be easily replicated by agencies to develop their own network screening corridor-level models and expedite the identification of corridors in need of safety improvements to reduce FI crashes. Existing site-level network screening methods can be used to supplement the developed corridor-level methodology by identifying high-risk sites within identified high-risk corridors.

Modeling the risk of wrong-way driving at the exit ramp terminals of partial cloverleaf interchanges

INTRODUCTION

Partial cloverleaf (parclo) interchanges with closely spaced parallel entrance and exit ramps are more prone to wrong-way driving (WWD) compared to other interchange types. In this study, a logistic regression model was developed to predict the risk of WWD at the exit ramp terminals of parclo interchanges.

METHOD

The logistic regression model was developed using Firth's penalized likelihood techniques based on the predictor variables such as exit ramp geometric design features, wrong-way related traffic control devices, area type, and traffic volume.

RESULTS

According to the model, the significant predictors of WWD at parclo exit ramp terminals include corner radius from crossroad to entrance ramp, type of median on crossroad, width of median on two-way ramp, channelizing island, distance to the nearest access point, "Keep Right" sign, wrong-way arrow, intersection signalization, and traffic volume at the exit and entrance ramps. This model was used to conduct network screening for all the exit ramp terminals of parclo interchanges in Alabama and Georgia to identify high-risk locations in these two states. Seven high-risk locations were monitored by video cameras for 48-hours to observe the occurrences of WWD incidents. Results suggest that two locations in Alabama and two locations in Georgia experienced multiple WWD incidents within 48-hours of a typical weekend.

CONCLUSION

The observation of WWD incidents at high-risk locations demonstrates strong evidence that the model could identify the exit ramp terminals with high risk of WWD.

PRACTICAL APPLICATIONS

Transportation agencies can use this model to assess the risk of WWD at the exit ramp terminals within their jurisdictions and identify the high-risk locations for countermeasures implementation.

Empirical Bayes application on low-volume roads: Oregon case study

INTRODUCTION

This paper investigates the Empirical Bayes (EB) method and the Highway Safety Manual (HSM) predictive methodology for network screening on low-volume roads in Oregon.

METHOD

A study sample of around 870 miles of rural two-lane roadways with extensive crash, traffic and roadway information was used in this investigation. To understand the effect of low traffic exposure in estimating the EB expected number of crashes, the contributions of both the observed and the HSM predicted number of crashes were analyzed.

RESULTS AND CONCLUSIONS

The study found that, on low-volume roads, the predicted number of crashes is the major contributor in estimating the EB expected number of crashes. The study also found a large discrepancy between the observed and the predicted number of crashes using the HSM procedures calibrated for the state of Oregon, which could partly be attributed to the unique attributes of low-volume roads that are different from the rest of the network. However, the expected number of crashes for the study sample using the HSM EB method was reasonably close to the observed number of crashes over the 10-year study period. Practical Applications: Based on the findings, it can still be very effective to use network screening methods that rely primarily on risk factors for low-volume road networks. This is especially applicable in situations where accurate and reliable crash data are not available.

Crash analysis and development of safety performance functions for Florida roads in the framework of the context classification system

INTRODUCTION

Safety performance functions (SPF) are employed to predict crash counts at the different roadway elements. Several SPFs were developed for the various roadway elements based on different classifications such as functional classification and area type. Since a more detailed classification of roadway elements leads to more accurate crash predictions, multiple states have developed new classification systems to classify roads based on a comprehensive classification. In Florida, the new roadway context classification system incorporates geographic, demographic, and road characteristics information.

METHOD

In this study, SPFs were developed in the framework of the FDOT roadway context classification system at three levels of modeling, context classification (CC-SPFs), area type (AT-SPFs), and statewide (SW-SPF) levels. Crash and traffic data from 2015-2019 were obtained. Road characteristics and road environment information have also been gathered along Florida roads for the SPF development.

RESULTS

The developed SPFs showed that there are several variables that influence the frequency of crashes, such as annual average daily traffic (AADT), signalized intersections and access point densities, speed limit, and shoulder width. However, there are other variables that did not have an influence in crash occurrence such as concrete surface and the presence of bicycle slots. CC-SPFs had the best performance among others. Moreover, network screening to determine the most problematic road segments has been accomplished. The results of the network screening indicated that the most problematic roads in Florida are the suburban commercial and the urban general roads. Practical Applications: This research provides a solid reference for decision-makers regarding crash prediction and safety improvement along Florida roads.

A GIS approach to the development of a segment-level derailment prediction model

Train related accidents, particularly derailments, can lead to severe consequences especially when they involve injuries or fatalities or when they involve hazardous materials that might result in environmental impacts. Whereas numerous road safety studies have suggested appropriate approaches to predicting vehicle-to-vehicle collisions, very few railway safety studies have considered predicting the number of derailments on rail tracks in North America. In addition, the existing few rail safety assessment and derailment prediction models have often been constrained by aggregated data limiting the safety assessments by, for example, failing to consider segment-level characteristics. This paper focused on the development of an integrated database for the development of a segment-level derailment prediction model for Canada's rail network. The primary objective of this paper is to report how challenges in the data integration process were overcome and also to develop a network screening tool to identify segments with high derailment risk in Canada's rail network. Negative binomial regression and the Empirical Bayes technique were used to estimate the predicted number of derailments on Canada's rail network at the segment level. A network screening process was then successfully applied to identify key segments of safety concern: the top ten segments of concern accounted for approximately 1% of the rail network allowing decision makers to focus their derailment mitigation efforts on a manageable part of Canada's vast rail network. The data processing approach and analysis in this study have strong implications for advancing research on rail safety in North America.

Generalized criteria for evaluating hotspot identification methods

Hotspot identification (HSID) is one of the most important components in the highway safety management process. Previous research has found that hazardous sites identified with different methods are not consistent. It is therefore necessary to evaluate the performance of various HSID methods. The existing evaluation criteria are limited to two consecutive periods, and do not consider the temporal instability of crashes. In addition, one existing criterion does not precisely evaluate HSID method under given circumstances. This paper proposed three generalized criteria to evaluate the performance of HSID methods: (1) High Crashes Consistency Test (HCCT) is proposed to evaluate HSID methods in terms of their reliabilities of identifying sites with high crash counts; (2) Common Sites Consistency Test (CSCT) is proposed to gauge HSID methods in consistently identifying a set of common sites as hazardous sites; and, (3) Absolute Rank Differences Test (ARDT) is proposed to measure the consistency of HSID methods in measuring the absolute differences in rankings. Further, three commonly used HSID methods are applied to estimate crashes on Texas rural two-lane roadway segments with eight years of crash data. The performance of these three HSID methods were evaluated to validate the proposed criteria. Comparisons between the existing criteria and the generalized criteria revealed that: (1) the generalized criteria are capable of evaluating different HSID methods over multiple periods; and (2) the generalized criteria are enhanced with a consistent result and with less discrepancy in scores of the best identified HSID method.

Network screening for large urban road networks: Using GPS data and surrogate measures to model crash frequency and severity

Crash frequency and injury severity are independent dimensions defining crash risk in road safety management and network screening. Traditional screening techniques model crashes using regression and historical crash data, making them intrinsically reactive. In response, surrogate measures of safety have become a popular proactive alternative. The purpose of this paper is to develop models for crash frequency and severity incorporating GPS-derived surrogate safety measures (SSMs) as predictive variables. SSMs based on vehicle manoeuvres and traffic flow were extracted from data collected in Quebec City. The mixed multivariate outcome is estimated using two models; a Full Bayes Spatial Negative Binomial model for crash frequency estimated using the Integrated Nested Laplace Approximation approach and a fractional Multinomial Logit model for crash severity. Model outcomes are combined to generate posterior expected crash frequency at each severity level and rank sites based on crash cost. The crash frequency model was accurate at the network scale, with the majority of proposed SSMs statistically significant at 95% confidence and the direction of their effect generally consistent with previous research. In the crash severity model, fewer variables were significant, yet the direction of the effect of all significant variables was again consistent with previous research. Correlations between rankings predicted by the mixed multivariate model and by the crash data were adequate for intersections (0.46) but were poorer for links (0.25). The ability to prioritize sites based on GPS data and SSMs rather than historical crash data represents a substantial contribution to the field of road safety.

Dynamic programming-based hot spot identification approach for pedestrian crashes

Network screening techniques are widely used by state agencies to identify locations with high collision concentration, also referred to as hot spots. However, most of the research in this regard has focused on identifying highway segments that are of concern to automobile collisions. In comparison, pedestrian hot spot detection has typically focused on analyzing pedestrian crashes in specific locations, such as at/near intersections, mid-blocks, and/or other crossings, as opposed to long stretches of roadway. In this context, the efficiency of the some of the widely used network screening methods has not been tested. Hence, in order to address this issue, a dynamic programming-based hot spot identification approach is proposed which provides efficient hot spot definitions for pedestrian crashes. The proposed approach is compared with the sliding window method and an intersection buffer-based approach. The results reveal that the dynamic programming method generates more hot spots with a higher number of crashes, while providing small hot spot segment lengths. In comparison, the sliding window method is shown to suffer from shortcomings due to a first-come-first-serve approach vis-à-vis hot spot identification and a fixed hot spot window length assumption.

Applying quantile regression for modeling equivalent property damage only crashes to identify accident blackspots

Hot spot identification (HSID) aims to identify potential sites-roadway segments, intersections, crosswalks, interchanges, ramps, etc.-with disproportionately high crash risk relative to similar sites. An inefficient HSID methodology might result in either identifying a safe site as high risk (false positive) or a high risk site as safe (false negative), and consequently lead to the misuse the available public funds, to poor investment decisions, and to inefficient risk management practice. Current HSID methods suffer from issues like underreporting of minor injury and property damage only (PDO) crashes, challenges of accounting for crash severity into the methodology, and selection of a proper safety performance function to model crash data that is often heavily skewed by a preponderance of zeros. Addressing these challenges, this paper proposes a combination of a PDO equivalency calculation and quantile regression technique to identify hot spots in a transportation network. In particular, issues related to underreporting and crash severity are tackled by incorporating equivalent PDO crashes, whilst the concerns related to the non-count nature of equivalent PDO crashes and the skewness of crash data are addressed by the non-parametric quantile regression technique. The proposed method identifies covariate effects on various quantiles of a population, rather than the population mean like most methods in practice, which more closely corresponds with how black spots are identified in practice. The proposed methodology is illustrated using rural road segment data from Korea and compared against the traditional EB method with negative binomial regression. Application of a quantile regression model on equivalent PDO crashes enables identification of a set of high-risk sites that reflect the true safety costs to the society, simultaneously reduces the influence of under-reported PDO and minor injury crashes, and overcomes the limitation of traditional NB model in dealing with preponderance of zeros problem or right skewed dataset.

Application of Poisson random effect models for highway network screening

In recent years, Bayesian random effect models that account for the temporal and spatial correlations of crash data became popular in traffic safety research. This study employs random effect Poisson Log-Normal models for crash risk hotspot identification. Both the temporal and spatial correlations of crash data were considered. Potential for Safety Improvement (PSI) were adopted as a measure of the crash risk. Using the fatal and injury crashes that occurred on urban 4-lane divided arterials from 2006 to 2009 in the Central Florida area, the random effect approaches were compared to the traditional Empirical Bayesian (EB) method and the conventional Bayesian Poisson Log-Normal model. A series of method examination tests were conducted to evaluate the performance of different approaches. These tests include the previously developed site consistence test, method consistence test, total rank difference test, and the modified total score test, as well as the newly proposed total safety performance measure difference test. Results show that the Bayesian Poisson model accounting for both temporal and spatial random effects (PTSRE) outperforms the model that with only temporal random effect, and both are superior to the conventional Poisson Log-Normal model (PLN) and the EB model in the fitting of crash data. Additionally, the method evaluation tests indicate that the PTSRE model is significantly superior to the PLN model and the EB model in consistently identifying hotspots during successive time periods. The results suggest that the PTSRE model is a superior alternative for road site crash risk hotspot identification.