Hidden patterns among the fatally injured pedestrians in an Iranian population: application of categorical principal component analysis (CATPCA)

A Fuzzy Clustering Approach to Identify Pedestrians' Traffic Behavior Patterns

BACKGROUND

Pattern recognition of pedestrians' traffic behavior can enhance the management efficiency of interested groups by targeting access to them and facilitating planning via more specific surveys. This study aimed to evaluate the pedestrians' traffic behavior pattern by fuzzy clustering algorithm and assess the factors related to higher-risk traffic behavior of pedestrians. Study Design: This study is a secondary methodological study based on the data from a cross-sectional study.

METHODS

The fuzzy c-means (FCM), as a machine learning clustering method, was conducted to identify the pattern of traffic behaviors by collecting data from 600 pedestrians in Urmia, Iran via "the Pedestrian Behavior Questionnaire" (PBQ) and using 5 domains of PBQ. Multiple logistic regression was fitted to identify risk factors of traffic behaviors.

RESULTS

Results revealed two clusters consisting of lower-risk and higher-risk behaviors. The majority of pedestrians (64.33%) were in the lower-risk cluster. Subjects≤33 years old (Odds ratio [OR]=1.92, P<0.001), subjects with≤6 years of education (OR=1.74, P=0.010), males (OR=1.90, P=0.001), unmarried pedestrians (OR=3.61, P=0.007), and users of public transportation (OR=2.01, P=0.002) were more likely to have higher-risk traffic behavior.

CONCLUSION

We identified traffic behavior patterns of Urmia pedestrians with lower-risk and higher-risk behaviors via FCM. The findings from this study would be helpful for policymakers to promote safety measures and train pedestrians.

Predictors of pre-hospital vs. hospital mortality due to road traffic injuries in an Iranian population: results from Tabriz integrated road traffic injury registry

Background

Road Traffic Injuries (RTIs) is considered as one of the main health challenges and causes of mortality, worldwide and especially in Iran. Predicting the place where RTIs-related death takes place is vital in decreasing this type of mortality. The purpose of the present study was to identify the predictors of RTI fatalities with respect to the place of death (hospital vs. pre-hospital) during the recent decade in East Azerbaijan Province, Iran.

Methods

Overall, 7347 RTI fatalities were retrieved from the road traffic injuries registry which is supported by the Forensic Medicine Organization in East Azerbaijan. Among these cases, 2758(37.5%)) were hospital deaths. The registered variables of these cases were analysed using bivariate and multiple logistic regression (STATA version 15).

Results

Out of 7347 deaths, 5862 (79.8%) were men and the rest were women 1485 (20.2%).The mean age was 40.3 (SD = 20.8). Of the total number of cases, 2758 (37.5%) died in hospital death and the rest 4589 (62.5) were pre-hospital death. According to the results of the present study, inter-city RTI (OR = 1.7, CI 95% = (1.5–2)) and RTIs inside the city of Tabriz (OR = 1.4, CI 95% = (1.2–1.6)) increases the chance of hospitals death. In addition, having a heavy counterpart vehicle compared to no counterpart vehicle decreased the chances of hospitals death (OR = 0.46, CI 95% = (0.39–0.55)) while motorcycle or bike counterpart vehicle compared to no counterpart vehicle increased the chances of hospital death (OR = 2.26, CI 95% = (1.59–3.22)). Also the users of the motorcycle or bike vehicle compared to the pedestrians increased the chances of hospital death (OR = 1.43, CI 95% = (1.19–1.71)) while any the other vehicle users compared to the pedestrians have significantly lower chances for hospital death. Other factors that increased hospitals death were transferring injured people by ambulance (OR = 1.3, CI 95% = (1.1–1.6)) and being elderly (OR = 1.5, CI 95% = (1.2–1.7)). Moreover, it was found that the annual trend of change in hospital death is strongly affected by the above-identified factors.

Conclusions

The effective predictors in hospital death were RTI location, type of counterpart vehicle, used vehicles and lighting condition. The identified factors related to the location of deaths by RTI can be divided into the RTI severity-related factors as well as factors related to the services quality and speed of delivery. According to the present results, through professional training of people in the field and providing immediate assistance in RTIs pre-hospital mortality can be significantly prevented.

Applying count time series to assess 13-year pedestrian mortality trend caused by traffic accidents in East-Azerbaijan province, Iran

In populated cities, pedestrian mortality is higher compared to other traffic mortalities. The current study aimed to describe the trend of pedestrian mortality in the East-Azerbaijan (Northwest of Iran) province from 2006 to 2019 and find the factors that affect the mortality number. Pedestrian mortality data from March 2006 to March 2019 was obtained from the Legal Medicine Organization database of Iran. Generalized Linear Auto Regressive Moving Average (GLARMA) models were used to assess the trend, and affecting factors of pedestrian mortality. According to the traffic accident data from 21 March 2006 until 20 March 2019 in East-Azerbaijan 24.11% of mortalities are related to pedestrians. Pedestrian mortality had a decreasing seasonal trend during 2006-2019. The result of the GLARMA model showed that age >65, being non-educated, cases with head trauma death cause, pre-hospital death, accident inside the city, vehicle type and self-employed jobs had a direct relation to pedestrian's mortality.