Predicting and Analyzing Road Traffic Injury Severity Using Boosting-Based Ensemble Learning Models with SHAPley Additive exPlanations

Sheng Dong; Afaq Khattak; Irfan Ullah; Jibiao Zhou; Arshad Hussain

doi:10.3390/ijerph19052925

Predicting and Analyzing Road Traffic Injury Severity Using Boosting-Based Ensemble Learning Models with SHAPley Additive exPlanations

Int J Environ Res Public Health. 2022 Mar 2;19(5):2925. doi: 10.3390/ijerph19052925.

Authors

Sheng Dong¹, Afaq Khattak², Irfan Ullah³, Jibiao Zhou⁴, Arshad Hussain⁵

Affiliations

¹ School of Civil and Transportation Engineering, Ningbo University of Technology, Fenghua Road No. 201, Ningbo 315211, China.
² The Key Laboratory of Road and Traffic Engineering, Ministry of Education, Tongji University, 4800 Cao'an Road, Jiading, Shanghai 201804, China.
³ Department of Civil Engineering, International Islamic University, Sector H-10, Islamabad 1243, Pakistan.
⁴ College of Transportation Engineering, Tongji University, 4800 Cao'an Road, Jiading, Shanghai 201804, China.
⁵ NUST Institute of Civil Engineering, National University of Sciences and Technology, Sector H-12, Islamabad 44000, Pakistan.

Abstract

Road traffic accidents are one of the world's most serious problems, as they result in numerous fatalities and injuries, as well as economic losses each year. Assessing the factors that contribute to the severity of road traffic injuries has proven to be insightful. The findings may contribute to a better understanding of and potential mitigation of the risk of serious injuries associated with crashes. While ensemble learning approaches are capable of establishing complex and non-linear relationships between input risk variables and outcomes for the purpose of injury severity prediction and classification, most of them share a critical limitation: their "black-box" nature. To develop interpretable predictive models for road traffic injury severity, this paper proposes four boosting-based ensemble learning models, namely a novel Natural Gradient Boosting, Adaptive Gradient Boosting, Categorical Gradient Boosting, and Light Gradient Boosting Machine, and uses a recently developed SHapley Additive exPlanations analysis to rank the risk variables and explain the optimal model. Among four models, LightGBM achieved the highest classification accuracy (73.63%), precision (72.61%), and recall (70.09%), F1-scores (70.81%), and AUC (0.71) when tested on 2015-2019 Pakistan's National Highway N-5 (Peshawar to Rahim Yar Khan Section) accident data. By incorporating the SHapley Additive exPlanations approach, we were able to interpret the model's estimation results from both global and local perspectives. Following interpretation, it was determined that the Month_of_Year, Cause_of_Accident, Driver_Age and Collision_Type all played a significant role in the estimation process. According to the analysis, young drivers and pedestrians struck by a trailer have a higher risk of suffering fatal injuries. The combination of trailers and passenger vehicles, as well as driver at-fault, hitting pedestrians and rear-end collisions, significantly increases the risk of fatal injuries. This study suggests that combining LightGBM and SHAP has the potential to develop an interpretable model for predicting road traffic injury severity.

Keywords: SHapley Additive exPlanations; boosting-based ensemble models; road traffic injuries; traffic safety.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Accidents, Traffic*
Data Collection
Humans
Machine Learning
Motor Vehicles
Pedestrians*