Citation

Behzadi Goodari M, Sharifi H, Dehesh P, Mosleh-Shirazi MA, Dehesh T. Sci. Rep. 2023; 13(1): e6662.

Copyright

(Copyright © 2023, Nature Publishing Group)

DOI

10.1038/s41598-023-33571-8

PMID

37095125

PMCID

PMC10125984

Abstract

Road traffic accidents (RTAs) are among the top causes of mortality and disability globally, particularly in developing nations like Iran. In this study, RTAs were analyzed to develop precise predictive models for predicting the frequency of accidents in the Kerman Province (southeastern Iran) using the autoregressive integrated moving average (ARIMA) and autoregressive integrated moving average with explanatory variables (ARIMAX) modeling methods. The findings demonstrate that including factors regarding humans, vehicles, and elements of nature in the time-series analysis of accident records resulted in the development of a more reliable prediction model than utilizing only aggregated accident count. The understanding of safety on the road is increased by this research, which also offers a method for forecasting that utilizes a variety of parameters relating to people, cars, and the environment. The findings of this research are likely to contribute to lowering the incidence of RTAs in Iran.

Language: en

Keywords

Humans; Incidence; Forecasting; *Accidents, Traffic; *Automobiles; Iran/epidemiology