ABSTRACT
BACKGROUND: The coronavirus disease (COVID-19) effected a global health crisis in 2019, 2020, and beyond. Currently, methods such as temperature detection, clinical manifestations, and nucleic acid testing are used to comprehensively determine whether patients are infected with the severe acute respiratory syndrome coronavirus 2. However, during the peak period of COVID-19 outbreaks and in underdeveloped regions, medical staff and high-tech detection equipment were limited, resulting in the continued spread of the disease. Thus, a more portable, cost-effective, and automated auxiliary screening method is necessary. OBJECTIVE: We aim to apply a machine learning algorithm and non-contact monitoring system to automatically screen potential COVID-19 patients. METHODS: We used impulse-radio ultra-wideband radar to detect respiration, heart rate, body movement, sleep quality, and various other physiological indicators. We collected 140 radar monitoring data from 23 COVID-19 patients in Wuhan Tongji Hospital and compared them with 144 radar monitoring data from healthy controls. Then, the XGBoost and logistic regression (XGBoost + LR) algorithms were used to classify the data according to patients and healthy subjects. RESULTS: The XGBoost + LR algorithm demonstrated excellent discrimination (precision = 92.5%, recall rate = 96.8%, AUC = 98.0%), outperforming other single machine learning algorithms. Furthermore, the SHAP value indicates that the number of apneas during REM, mean heart rate, and some sleep parameters are important features for classification. CONCLUSION: The XGBoost + LR-based screening system can accurately predict COVID-19 patients and can be applied in hotels, nursing homes, wards, and other crowded locations to effectively help medical staff.
Subject(s)
COVID-19 , Humans , Logistic Models , Monitoring, Physiologic , Radar , SARS-CoV-2ABSTRACT
BACKGROUND: Osteoarthritis (OA) is a metabolic disorder and able to be relieved by traditional Chinese medicines. However, the effect of Ligusticum wallichii on OA is unknown. METHODS: Cytokine IL-1ß and L. wallichii extracts were used to stimulate the primary mouse chondrocytes. MTT assay was used to measure the cell viability. The mRNA and protein level of each gene were test by qRT-PCR and western blotting, respectively. The rate of apoptotic cell was measured by flow cytometry. GC/MS-based metabolomics was utilized to characterize the variation of metabolome. RESULTS: Here, we found that L. wallichii attenuated the IL-1ß-induced apoptosis, inflammatory response, and extracellular matrix (ECM) degradation in mouse chondrocytes. Then we used GC/MS-based metabolomics to characterize the variation of metabolomes. The established metabolic profile of mouse chondrocytes showed that the abundance of most metabolites (n = 40) altered by IL-1ß stimulation could be repressed by L. wallichii treatment. Multivariate data analysis identified that cholesterol, linoleic acid, hexadecandioic acid, proline, l-valine, l-leucine, pyruvate, palmitic acid, and proline are the most key biomarkers for understanding the metabolic role of L. wallichii in IL-1ß-treated chondrocytes. Further pathway analysis using these metabolites enriched fourteen metabolic pathways, which were dramatically changed in IL-1ß-treated chondrocytes and capable of being reprogrammed by L. wallichii incubation. These enriched pathways were involved in carbon metabolisms, fatty acid biosynthesis, and amino acid metabolisms. CONCLUSIONS: These findings provide potential clues that metabolic strategies are linked to protective mechanisms of L. wallichii treatment in IL-1ß-stimulated chondrocytes and emphasize the importance of metabolic strategies against inflammatory responses in OA development.
ABSTRACT
The vehicle to pedestrian (V2P) applications will enable safety, mobility, and environmental advancements for the vulnerable roadway user (VRU) that current technologies are unable to provide. The present research aims to explore the use of random parameters in logit models to examine factors that significantly influence injury severity of VRU involved crashes. Two types of logit models, the mixed generalized ordered logit (MGOL) models and mixed logit models are proposed to provide insights on reducing injury severities of pedestrian and bicyclist involved crashes and benefit amending current V2P applications to address the special safety needs and challenges of these VRUs. Based on 9180 pedestrian involved crashes and 1402 bicyclist involved crashes from the Fatality Analysis Reporting System (FARS), the measure of injury severities - time-to-death is considered as the independent variables to capture a more comprehensive picture of events after a crash occurs. By comparing to the ordered logit models and the multinomial logit models, the effectiveness and appropriateness of the proposed models are verified through two perspectives - goodness of fit and predictive power. The modelling results show that the injury severity of VRU involved crashes is significantly associated with involved non-motorist characteristics (age and police reported alcohol involvement), involved motorist characteristics (drunk drivers, previous recorded crashes, number of occupants), involved vehicle characteristics (vehicle body type, vehicle model year, travel speed), roadway characteristics (interstate, junction, roadway profile), and environmental characteristics (light and weather condition). Among these significant factors, the number of occupants, vehicle body type, interstate, and junction result in random parameters, which capture and reflect the unobserved heterogeneity across sampled observations. The analyses of under-researched aspects of VRU involved crashes, that is time-to-death, help us develop a deeper understanding of the consequences of injury and ultimately health and social costs. The findings indicate that the proposed MGOL models and mixed logit models can account for the heterogeneity issues in crash data due to the unobserved factors. In addition, the injury severity models that incorporate the random parameter features can reveal new insights and have superior goodness of fit.
Subject(s)
Accidents, Traffic/statistics & numerical data , Wounds and Injuries/etiology , Adolescent , Adult , Bicycling/injuries , Child , Child, Preschool , Female , Humans , Infant , Injury Severity Score , Male , Middle Aged , Models, Statistical , Pedestrians/statistics & numerical data , Risk Factors , Safety , Wounds and Injuries/epidemiology , Young AdultABSTRACT
Conventional traffic crash analyzing methods focus on identifying the relationship between traffic crash outcomes and impact risk factors and explaining the effects of risk factors, which ignore the changes of roadway systems and can lead to inaccurate results in traffic crash predictions. To address this issue, an innovative two-step method is proposed and a support vector regression (SVR) model is formulated into state-space model (SSM) framework for traffic crash prediction. The SSM was developed in the first step to identify the dynamic evolution process of the roadway systems that are caused by the changes of traffic flow and predict the changes of impact factors in roadway systems. Using the predicted impact factors, the SVR model was incorporated in the second step to perform the traffic crash prediction. A five-year dataset that obtained from 1152 roadway segments in Tennessee was employed to validate the model effectiveness. The proposed models result in an average prediction MAPE of 7.59%, a MAE of 0.11, and a RMSD of 0.32. For the performance comparison, a SVR model and a multivariate negative binomial (MVNB) model were developed to do the same task. The results show that the proposed model has superior performances in terms of prediction accuracy compared to the SVR and MVNB models. Compared to the SVR and MVNB models, the benefit of incorporating a state-space model to identify the changes of roadway systems is significant evident in the proposed models for all crash types, and the prediction accuracy that measured by MAPE can be improved by 4.360% and 6.445% on average, respectively. Apart from accuracy improvement, the proposed models are more robust and the predictions can retain a smoother pattern. Furthermore, the results show that the proposed model has a more precise and synchronized response behavior to the high variations of the observed data, especially for the phenomenon of extra zeros.
Subject(s)
Accidents, Traffic/statistics & numerical data , Accidents, Traffic/prevention & control , Databases, Factual , Environment Design/statistics & numerical data , Humans , Models, Theoretical , Multivariate Analysis , Regression Analysis , Risk Factors , Support Vector Machine , TennesseeABSTRACT
INTRODUCTION: Existing research indicates that around 90% of all U.S. residents have access to at least one level I or II trauma center within 60min. However, a limitation of these estimates lies in that they are based on where people live and not where people are injured, which may overestimate the access to trauma centers for seriously injured patients in fatal crashes. METHOD: In this study, the Fatality Analysis Reporting System (FARS) data between 2013 and 2014 were collected and analyzed to quantify the access of injured patients to trauma centers for fatal crashes across states. Two types of distance, linear distance and route distance, were calculated using ArcGIS. The estimated transport time to the nearest level I/II trauma center was also calculated and compared to the recorded on-scene and transport time. RESULTS AND CONCLUSIONS: The Northeast region had the nearest average linear and route distance between fatal crash and trauma center (25.3km and 31.7km, respectively), followed by the Midwest (44.4km and 54.1km), the South (47.3km and 57.0km), and the West (50.9km and 67.5km). The comparison between the estimated and actual transport time revealed that the different states adopted different trauma triage protocols, resulting in different utilization rates of the level I/II trauma center among states. A linear regression analysis demonstrated that the longer the average route distance, the less the seriously injured patients in fatal crashes were taken to level I/II trauma center directly. Practical applications: These findings may help to identify the access to trauma centers for road crashes and the variation of delivery ratio to trauma center among the states, therefore a better utilization of trauma centers for road crashes can be achieved for the emergency medical services (EMS) systems.
Subject(s)
Accidents, Traffic/statistics & numerical data , Trauma Centers/supply & distribution , Humans , Linear Models , Trauma Centers/statistics & numerical data , United StatesABSTRACT
Highway safety laws aim to influence driver behaviors so as to reduce the frequency and severity of crashes, and their outcomes. For one specific highway safety law, it would have different effects on the crashes across severities. Understanding such effects can help policy makers upgrade current laws and hence improve traffic safety. To investigate the effects of highway safety laws on crashes across severities, multivariate models are needed to account for the interdependency issues in crash counts across severities. Based on the characteristics of the dependent variables, multivariate dynamic Tobit (MVDT) models are proposed to analyze crash counts that are aggregated at the state level. Lagged observed dependent variables are incorporated into the MVDT models to account for potential temporal correlation issues in crash data. The state highway safety law related factors are used as the explanatory variables and socio-demographic and traffic factors are used as the control variables. Three models, a MVDT model with lagged observed dependent variables, a MVDT model with unobserved random variables, and a multivariate static Tobit (MVST) model are developed and compared. The results show that among the investigated models, the MVDT models with lagged observed dependent variables have the best goodness-of-fit. The findings indicate that, compared to the MVST, the MVDT models have better explanatory power and prediction accuracy. The MVDT model with lagged observed variables can better handle the stochasticity and dependency in the temporal evolution of the crash counts and the estimated values from the model are closer to the observed values. The results show that more lives could be saved if law enforcement agencies can make a sustained effort to educate the public about the importance of motorcyclists wearing helmets. Motor vehicle crash-related deaths, injuries, and property damages could be reduced if states enact laws for stricter text messaging rules, higher speeding fines, older licensing age, and stronger graduated licensing provisions. Injury and PDO crashes would be significantly reduced with stricter laws prohibiting the use of hand-held communication devices and higher fines for drunk driving.
Subject(s)
Accidents, Traffic , Automobile Driving/legislation & jurisprudence , Safety/legislation & jurisprudence , Accidents, Traffic/mortality , Accidents, Traffic/prevention & control , Accidents, Traffic/statistics & numerical data , Effect Modifier, Epidemiologic , Humans , Licensure/legislation & jurisprudence , Models, TheoreticalABSTRACT
Recent research demonstrates the appropriateness of multivariate regression models in crash count modelling when one specific type of crash counts needs to be analysed, since they can better handle the correlated issues in multiple crash counts. In this paper, a random-parameter multivariate zero-inflated Poisson (RMZIP) regression model is proposed as an alternative multivariate methodology for jointly modelling crash counts simultaneously. Using this RMZIP model, we are able to account for the heterogeneity due to the unobserved roadway geometric design features and traffic characteristics. Our formulation also has the merit of handling excess zeros in correlated crash counts, a phenomenon that is commonly found in practice. The Bayesian method is employed to estimate the model parameters. We use the proposed modelling framework to predict crash frequencies at urban signalized intersections in Tennessee. To investigate the model performances, three models - a fixed-parameter MZIP model, a random-parameter multivariate negative binomial (RMNB) model, and a random-parameter multivariate zero-inflated negative binomial (RMZINB) model - have been employed as the comparison methods. The comparison results show that the proposed RMZIP models provide a satisfied statistical fit with more variables producing statistically significant parameters. In other word, the RMZIP models have the potential to provide a fuller understanding of how the factors affect crash frequencies on specific roadway intersections. A variety of variables are found to significantly influence the crash frequencies by varying magnitudes. These variables result in random parameters and thereby their effects on crash frequencies are found to vary significantly across the sampled intersections.
Subject(s)
Accidents, Traffic , Accidents, Traffic/statistics & numerical data , Environment Design , Models, Statistical , Poisson DistributionABSTRACT
To investigate the relationship between crash frequency and potential influence factors, the accident data for events occurring on a 50km long expressway in China, including 567 crash records (2006-2008), were collected and analyzed. Both the fixed-length and the homogeneous longitudinal grade methods were applied to divide the study expressway section into segments. A negative binomial (NB) model and a random effect negative binomial (RENB) model were developed to predict crash frequency. The parameters of both models were determined using the maximum likelihood (ML) method, and the mixed stepwise procedure was applied to examine the significance of explanatory variables. Three explanatory variables, including longitudinal grade, road width, and ratio of longitudinal grade and curve radius (RGR), were found as significantly affecting crash frequency. The marginal effects of significant explanatory variables to the crash frequency were analyzed. The model performance was determined by the relative prediction error and the cumulative standardized residual. The results show that the RENB model outperforms the NB model. It was also found that the model performance with the fixed-length segment method is superior to that with the homogeneous longitudinal grade segment method.
Subject(s)
Accidents, Traffic/statistics & numerical data , Environment Design/statistics & numerical data , Models, Statistical , China , Humans , Models, Theoretical , Motor Vehicles/statistics & numerical data , Probability , SafetyABSTRACT
OBJECTIVE: Distinguished from the traditional perspectives in crash analyses, which examined the effects of geometric design features, traffic factors, and other relevant attributes on the crash frequencies of roadway entities, our study focuses on exploring the effects of highway safety laws, as well as sociocultural characteristics, on fatal crashes across states. METHODS: Law and regulation related data were collected from the Insurance Institute for Highway Safety, State Highway Safety Offices, and Governors Highway Safety Association. A variety of sociodemographic characteristics were obtained from the U.S. Census Bureau. In addition, cultural factors and other attributes from a variety of resources are considered and incorporated in the modeling process. These data and fatal crash counts were collected for the 50 U.S. states and the District of Columbia and were analyzed using zero-truncated negative binomial (ZTNB) regression models. RESULTS: The results show that, in law and regulation-related factors, the use of speed cameras, no handheld cell phone ban, limited handheld cell phone ban, and no text messaging ban are found to have significant effects on fatal crashes. Regarding sociocultural characteristics, married couples with both husband and wife in the labor force are found to be associated with lower crash frequencies, the ratios of workers traveling to work by carpool, those driving alone, workers working outside the county of residence, language other than English and limited English fluency, and the number of licensed drivers are found to be associated with higher crash frequencies. CONCLUSIONS: Through reviewing and modeling existing state highway safety laws and sociocultural characteristics, the results reveal new insights that could influence policy making. In addition, the results would benefit amending existing laws and regulations and provide testimony about highway safety issues before lawmakers consider new legislation.
Subject(s)
Accidents, Traffic/legislation & jurisprudence , Accidents, Traffic/mortality , Automobile Driving/legislation & jurisprudence , Automobile Driving/statistics & numerical data , Safety/legislation & jurisprudence , Environment Design , Humans , United States , Wounds and Injuries/mortalityABSTRACT
Scavenger receptor class A, member 5 (SCARA5) is a member of the scavenger receptor family, and is involved in several types of human malignancy; however, its roles in osteosarcoma (OS) remain to be fully elucidated. Therefore, in the present study, the biological functions of SCARA5 in OS, and the potential underlying mechanisms were investigated. SCARA5 expression in OS tissues and cell lines was detected by reverse transcriptionquantitative polymerase chain reaction and western blot analysis. The effects of SCARA5 on the proliferation and migration/invasion ability of OS cells were determined by MTT and Transwell chamber assays, respectively. Expression levels of phosphorylated focal adhesion kinase (pFAK), FAK, pSrc, Src, matrix metalloproteinase (MMP)2 and MMP9 were evaluated via western blot analysis. The results of the present study demonstrated that SCARA5 was expressed at low levels in OS tissues and cell lines. The overexpression of SCARA5 significantly inhibited the proliferation, colony formation and migration/invasion abilities of the OS cells. Furthermore, SCARA5 significantly decreased the expression levels of pFAK, MMP2 and MMP9 in the OS cells. Taken together, these data suggested that the overexpression of SCARA5 inhibits tumor proliferation and invasion in OS via suppression of the FAK signaling pathway. Thus, novel therapeutic strategies or drugs targeted at SCARA5 may offer potential for the treatment of OS.
Subject(s)
Cell Proliferation , Scavenger Receptors, Class A/metabolism , Adolescent , Adult , Bone Neoplasms/metabolism , Bone Neoplasms/pathology , Case-Control Studies , Cell Line, Tumor , Cell Movement , Female , Focal Adhesion Kinase 1/metabolism , Gene Expression , Humans , Male , Middle Aged , Neoplasm Invasiveness , Osteosarcoma/metabolism , Osteosarcoma/pathology , Phosphorylation , Protein Processing, Post-Translational , Scavenger Receptors, Class A/genetics , Signal Transduction , Young AdultABSTRACT
OBJECTIVE: Crash injury results from complex interaction among factors related to at-fault driver's behavior, vehicle characteristics, and road conditions. Identifying the significance of these factors which affect crash injury severity is critical for improving traffic safety. A method was developed to explore the relationship based on crash data collected on rural two-lane highways in China. METHODS: There were 673 crash records collected on rural two-lane highways in China. A partial proportional odds model was developed to examine factors influencing crash injury severity owing to its high ability to accommodate the ordered response nature of injury severity. An elasticity analysis was conducted to quantify the marginal effects of each contributing factor. RESULTS: The results show that nine explanatory variables, including at-fault driver's age, at-fault driver having a license or not, alcohol usage, speeding, pedestrian involved, type of area, weather condition, pavement type, and collision type, significantly affect injury severity. In addition to alcohol usage and pedestrian involved, others violate the proportional odds assumption. At-fault driver's age of 25-39years, alcohol usage, speeding, pedestrian involved, pavement type of asphalt, and collision type of angle are found to be increased crash injury severity. PRACTICAL APPLICATIONS: The developed logit model has demonstrated itself efficient in identifying the effect of contributing factors on the crash injury severity.
Subject(s)
Accidents, Traffic/statistics & numerical data , Rural Population/statistics & numerical data , Wounds and Injuries/epidemiology , Adolescent , Adult , Age Factors , Alcohol Drinking/epidemiology , China/epidemiology , Female , Humans , Logistic Models , Male , Motor Vehicles/statistics & numerical data , Pedestrians/statistics & numerical data , Trauma Severity Indices , Weather , Young AdultABSTRACT
To address the dilemma between the need for truck transportation and the costs related to truck-involved crashes, the key is to identify the risk factors that significantly affect truck-involved crashes. The objective of this research is to estimate the effects of the characteristics of traffic, driver, geometry, and environment on severity of truck-involved crashes. Based on four crash severity categories (fatal/incapacitating, non-incapacitating, possible injury, and no injury/property damage only), a multinomial logit model is conducted to identify the risk factors. The investigation of risk ratios indicates that lower traffic volume with higher truck percentage is associated with more serious traffic crash with fatal/incapacitating injury while a non-standard geometric design is the main cause of non-incapacitating crashes. The influences of weather are significant for the possible-injury crashes while driver condition is the principal cause of no-injury/property-damage-only crashes. In addition, the statistical results demonstrate that the influence of the truck percentage is significant. One-unit change in the truck percentage will cause more than one times probability of being in an injury.
Subject(s)
Accidents, Traffic/classification , Accidents, Traffic/statistics & numerical data , Motor Vehicles/statistics & numerical data , Adult , Driving Under the Influence , Environment Design , Equipment Design , Female , Humans , Injury Severity Score , Male , Middle Aged , Models, Statistical , Risk Factors , Risk-Taking , Sex Factors , Tennessee , WeatherABSTRACT
Crash data are collected through police reports and integrated with road inventory data for further analysis. Integrated police reports and inventory data yield correlated multivariate data for roadway entities (e.g., segments or intersections). Analysis of such data reveals important relationships that can help focus on high-risk situations and coming up with safety countermeasures. To understand relationships between crash frequencies and associated variables, while taking full advantage of the available data, multivariate random-parameters models are appropriate since they can simultaneously consider the correlation among the specific crash types and account for unobserved heterogeneity. However, a key issue that arises with correlated multivariate data is the number of crash-free samples increases, as crash counts have many categories. In this paper, we describe a multivariate random-parameters zero-inflated negative binomial (MRZINB) regression model for jointly modeling crash counts. The full Bayesian method is employed to estimate the model parameters. Crash frequencies at urban signalized intersections in Tennessee are analyzed. The paper investigates the performance of MZINB and MRZINB regression models in establishing the relationship between crash frequencies, pavement conditions, traffic factors, and geometric design features of roadway intersections. Compared to the MZINB model, the MRZINB model identifies additional statistically significant factors and provides better goodness of fit in developing the relationships. The empirical results show that MRZINB model possesses most of the desirable statistical properties in terms of its ability to accommodate unobserved heterogeneity and excess zero counts in correlated data. Notably, in the random-parameters MZINB model, the estimated parameters vary significantly across intersections for different crash types.
Subject(s)
Accidents, Traffic/statistics & numerical data , Environment Design , Models, Statistical , Safety/statistics & numerical data , Accidents, Traffic/prevention & control , Bayes Theorem , Cities , Humans , Multivariate Analysis , Regression Analysis , TennesseeABSTRACT
The influence of intersection features on safety has been examined extensively because intersections experience a relatively large proportion of motor vehicle conflicts and crashes. Although there are distinct differences between passenger cars and large trucks-size, operating characteristics, dimensions, and weight-modeling crash counts across vehicle types is rarely addressed. This paper develops and presents a multivariate regression model of crash frequencies by collision vehicle type using crash data for urban signalized intersections in Tennessee. In addition, the performance of univariate Poisson-lognormal (UVPLN), multivariate Poisson (MVP), and multivariate Poisson-lognormal (MVPLN) regression models in establishing the relationship between crashes, traffic factors, and geometric design of roadway intersections is investigated. Bayesian methods are used to estimate the unknown parameters of these models. The evaluation results suggest that the MVPLN model possesses most of the desirable statistical properties in developing the relationships. Compared to the UVPLN and MVP models, the MVPLN model better identifies significant factors and predicts crash frequencies. The findings suggest that traffic volume, truck percentage, lighting condition, and intersection angle significantly affect intersection safety. Important differences in car, car-truck, and truck crash frequencies with respect to various risk factors were found to exist between models. The paper provides some new or more comprehensive observations that have not been covered in previous studies.