Predicting Road Accident Injury Severity for Drivers in Automobile Crashes in United States Using Machine Learning Models and AI

Aug 6, 2026

This study analyzes data from the National Highway Traffic Safety Administration’s 2021 Crash Report Sampling System to identify key factors driving injury severity in automobile crashes. Using multiple machine learning algorithms with cross-validation, it evaluates accuracy, sensitivity, precision, specificity, and AUC, supported by KNIME-based preprocessing and model building. Results show significant correlations between variables including airbag deployment, weather, intoxication, vehicle status, and driver distraction and the severity outcome. The work argues for stricter safety measures and recommends policy and prevention improvements.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages10

Reading Time25 min

AccessFree to download

Abstract

Introduction

Data Preparation and Data Understanding

University of Central Florida STARS Data Science and Data Mining Summer 2024 Predicting Road Accident Injury Severity for Drivers in Automobile Crashes in United States Using Machine Learning Models and AI Emil Agbemade University of Central Florida, [emil.agbemade@ucf.edu](emil.agbemade@ucf.edu) Benedict Kongyir Oklahoma State University, [bkongyi@okstate.edu](bkongyi@okstate.edu) Part of the Data Science Commons Find similar works at: [https://stars.library.ucf.edu/data-science-mining](https://stars.library.ucf.edu/data-science-mining) University of Central Florida Libraries [http://library.ucf.edu](http://library.ucf.edu) This Article is brought to you for free and open access by STARS. It has been accepted for inclusion in Data Science and Data Mining by an authorized administrator of STARS. For more information, please [contact](contact STARS@ucf.edu)[ STARS@ucf.edu](contact STARS@ucf.edu). STARS Citation Agbemade, Emil and Kongyir, Benedict, "Predicting Road Accident Injury Severity for Drivers in Automobile Crashes in United States Using Machine Learning Models and AI" (2024) . Data Science and Data Mining. 24. [https://stars.library.ucf.edu/data-science-mining/24](https://stars.library.ucf.edu/data-science-mining/24) Predicting Road Accident Injury Severity for Drivers in Automobile Crashes in United States Using Machine Learning Models and AI By: Benedict Kongyir, Oklahoma State University ([bkongyi@okstate.edu](bkongyi@okstate.edu) ) Emil Agbemade, University of Central Florida ([emil.agbemade@ucf.edu](emil.agbemade@ucf.edu) ) July 8, 2024 Abstract This study analyzes data from the National Highway Trafc Safety Administration’s 2021 Crash Report Sampling System to identify key factors contributing to the severity of injuries in car accidents. By utilizing various machine learning algorithms and cross-validation techniques, we assessed metrics such as accuracy, sensitivity, precision, specifcity, and the area under the curve (AUC) to evaluate the efectiveness of predictive models. All data preprocessing and model building was done using KNIME Analytical software [9] . Our fndings reveal signifcant correlations between certain variables such as airbag injection, weather conditions, intoxication, vehicle state, driver distractions, and injury severity. These insights underscore the importance of stringent safety measures, including proper restraint system usage and advanced driver-assistance technologies, in reducing the risk of severe injuries in car accidents. Recommendations for policy enhancements and preventive measures are discussed to improve overall vehicle safety. Introduction Car accidents remain a signifcant public health concern, leading to numerous injuries and fatalities each year. Understanding the factors that contribute to the severity of injuries in these incidents is crucial for developing efective safety regulations and policies. This report presents the results of a data analytics efort aimed at identifying the primary elements that most signifcantly infuence injury severity in car accidents. The dataset used in this study includes variables such as date, time of day, weather condi- tions, collision details, intoxication levels, vehicle state, and driver distractions. By analyzing these variables through several machine learning algorithms, we aimed to uncover trends, correlations, and insights that could inform the enhancement of car safety regulations and policies. Data for this study was sourced from the National Highway Trafc Safety Administration’s Crash Report Sampling System for the year 2021, comprising detailed information from police reports on each collision. Our analysis highlights several key factors that signifcantly increase the severity of injuries sustained in car accidents, demonstrating a strong predictive correlation with injury severity. The importance of these factors underscores the critical need for proper safety

FAQs

Which dataset and time scope does the study use?

The analysis uses the NHTSA Crash Report Sampling System, covering police-reported crashes from 2016 to 2021, with the study focusing on the 2021 Crash Report Sampling System in the described abstract.

How are predictive models evaluated in this work?

Models are assessed using metrics such as accuracy, sensitivity, precision, specificity, and the area under the curve (AUC) with cross-validation.

What variables show significant correlation with injury severity?

The findings highlight significant correlations involving airbag injection, weather conditions, intoxication, vehicle state, and driver distractions, relating them to injury severity.

Aug 6, 2026

Upload by Ava Thompson