Macro-Level Modeling of Traffic Crash Fatalities at the Scene: Insights for Road Safety

This study applied 2019 macro-level data from DATASUS to model traffic fatalities at the scene. Ordinary least squares (OLS) and censored regression models (TOBIT) were the methodologies used to identify the significant variables explaining the occurrence of deaths on public roads due to crashes. Th...

Full description

Saved in:
Bibliographic Details
Main Authors: Carlos Fabricio Assunção da Silva, Mauricio Oliveira de Andrade, Cintia Campos, Alex Mota dos Santos, Hélio da Silva Queiroz Júnior, Viviane Adriano Falcão
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Infrastructures
Subjects:
Online Access:https://www.mdpi.com/2412-3811/10/5/117
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849327008139444224
author Carlos Fabricio Assunção da Silva
Mauricio Oliveira de Andrade
Cintia Campos
Alex Mota dos Santos
Hélio da Silva Queiroz Júnior
Viviane Adriano Falcão
author_facet Carlos Fabricio Assunção da Silva
Mauricio Oliveira de Andrade
Cintia Campos
Alex Mota dos Santos
Hélio da Silva Queiroz Júnior
Viviane Adriano Falcão
author_sort Carlos Fabricio Assunção da Silva
collection DOAJ
description This study applied 2019 macro-level data from DATASUS to model traffic fatalities at the scene. Ordinary least squares (OLS) and censored regression models (TOBIT) were the methodologies used to identify the significant variables explaining the occurrence of deaths on public roads due to crashes. The number of fatalities on public roadways was then modeled using a multilayer perceptron artificial neural network employing the significant variables as predictors according to the generalization capacity of complex predictive models. The OLS and TOBIT findings indicated that the variables motorcycles and scooters per capita, municipal human development index, and number of SUS emergency units were the most important for modeling traffic fatalities at the scene at the national and regional levels. Applying these variables, the neural network’s best results achieved a hit rate of 88% for Brazil and 95% for the Northeast model. The contribution of this study is providing an approach combining various methods and considering a range of variables influencing traffic fatalities at the scene. The findings offer insights for policymakers, researchers, and practitioners involved in road safety initiatives, mainly where crash data are scarce, and macro-level analysis is necessary.
format Article
id doaj-art-69c38ba5d4e8472c98790a8e1e3d5462
institution Kabale University
issn 2412-3811
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Infrastructures
spelling doaj-art-69c38ba5d4e8472c98790a8e1e3d54622025-08-20T03:47:59ZengMDPI AGInfrastructures2412-38112025-05-0110511710.3390/infrastructures10050117Macro-Level Modeling of Traffic Crash Fatalities at the Scene: Insights for Road SafetyCarlos Fabricio Assunção da Silva0Mauricio Oliveira de Andrade1Cintia Campos2Alex Mota dos Santos3Hélio da Silva Queiroz Júnior4Viviane Adriano Falcão5Department of Cartographic Engineering, Center of Technologies and Geosciences, Federal University of Pernambuco, UFPE, Avenida Acadêmico Hélio Ramos, Cidade Universitária, s/n, Recife 50740-530, BrazilDepartment of Civil and Environmental Engineering, Center of Technologies and Geosciences, Federal University of Pernambuco, UFPE, Avenida da Engenharia, s/n-Cidade Universitária, Recife-Pernambuco 50670-420, BrazilFaculty of Science and Technology, Federal University of Goiás, Estrada Municipal, Lote 04, Sala 425, Fazenda Santo Antônio, Aparecida de Goiânia 74971-451, BrazilCenter of Agroforestry Sciences and Technologies, Federal University of Southern Bahia, Rodovia Ilhéus/Itabuna, Km 22, Itabuna 45604-811, BrazilDepartment of Civil and Environmental Engineering, Center of Technologies and Geosciences, Federal University of Pernambuco, UFPE, Avenida da Engenharia, s/n-Cidade Universitária, Recife-Pernambuco 50670-420, BrazilDepartment of Civil and Environmental Engineering, Center of Technologies and Geosciences, Federal University of Pernambuco, UFPE, Avenida da Engenharia, s/n-Cidade Universitária, Recife-Pernambuco 50670-420, BrazilThis study applied 2019 macro-level data from DATASUS to model traffic fatalities at the scene. Ordinary least squares (OLS) and censored regression models (TOBIT) were the methodologies used to identify the significant variables explaining the occurrence of deaths on public roads due to crashes. The number of fatalities on public roadways was then modeled using a multilayer perceptron artificial neural network employing the significant variables as predictors according to the generalization capacity of complex predictive models. The OLS and TOBIT findings indicated that the variables motorcycles and scooters per capita, municipal human development index, and number of SUS emergency units were the most important for modeling traffic fatalities at the scene at the national and regional levels. Applying these variables, the neural network’s best results achieved a hit rate of 88% for Brazil and 95% for the Northeast model. The contribution of this study is providing an approach combining various methods and considering a range of variables influencing traffic fatalities at the scene. The findings offer insights for policymakers, researchers, and practitioners involved in road safety initiatives, mainly where crash data are scarce, and macro-level analysis is necessary.https://www.mdpi.com/2412-3811/10/5/117traffic safetytraffic crash modelingtraffic managementtraffic fatalitiesmultiple linear regression
spellingShingle Carlos Fabricio Assunção da Silva
Mauricio Oliveira de Andrade
Cintia Campos
Alex Mota dos Santos
Hélio da Silva Queiroz Júnior
Viviane Adriano Falcão
Macro-Level Modeling of Traffic Crash Fatalities at the Scene: Insights for Road Safety
Infrastructures
traffic safety
traffic crash modeling
traffic management
traffic fatalities
multiple linear regression
title Macro-Level Modeling of Traffic Crash Fatalities at the Scene: Insights for Road Safety
title_full Macro-Level Modeling of Traffic Crash Fatalities at the Scene: Insights for Road Safety
title_fullStr Macro-Level Modeling of Traffic Crash Fatalities at the Scene: Insights for Road Safety
title_full_unstemmed Macro-Level Modeling of Traffic Crash Fatalities at the Scene: Insights for Road Safety
title_short Macro-Level Modeling of Traffic Crash Fatalities at the Scene: Insights for Road Safety
title_sort macro level modeling of traffic crash fatalities at the scene insights for road safety
topic traffic safety
traffic crash modeling
traffic management
traffic fatalities
multiple linear regression
url https://www.mdpi.com/2412-3811/10/5/117
work_keys_str_mv AT carlosfabricioassuncaodasilva macrolevelmodelingoftrafficcrashfatalitiesatthesceneinsightsforroadsafety
AT mauriciooliveiradeandrade macrolevelmodelingoftrafficcrashfatalitiesatthesceneinsightsforroadsafety
AT cintiacampos macrolevelmodelingoftrafficcrashfatalitiesatthesceneinsightsforroadsafety
AT alexmotadossantos macrolevelmodelingoftrafficcrashfatalitiesatthesceneinsightsforroadsafety
AT heliodasilvaqueirozjunior macrolevelmodelingoftrafficcrashfatalitiesatthesceneinsightsforroadsafety
AT vivianeadrianofalcao macrolevelmodelingoftrafficcrashfatalitiesatthesceneinsightsforroadsafety