Predicting Injury Severity in Urban Traffic Crashes: A Hybrid Method Integrating Decision Tree and Bayesian Network

Document Type : Original Article

Authors
Ali Tavakoli Kashani 1
Marzieh Rakhshani Moghadam 2
1 Associate Professor, School of Civil Engineering, Iran University of Science and Technology, Tehran, Iran and Road Safety Research Center, Iran University of Science and Technology, Tehran, Iran.
2 M.Sc., Grad., School of Civil Engineering, Iran University of Science and Technology, Tehran, Iran and Road Safety Research Center, Iran University of Science and Technology, Tehran, Iran.
10.22034/road.2025.527473.2406
Abstract
The impact of fast urbanization in Iran has led to increasing traffic congestion and crash risk for urban road users. Therefore, this study investigated factors influencing injury severity among road users (including pedestrians, vehicle drivers and passengers, and motorcyclists) using police-reported crash data from 2018 to 2022. For this purpose, a two-step framework was developed. Firstly, the Classification and Regression Tree (CART) method was applied to identify the most important factors affecting injury severity. In the second step, a Bayesian network model was employed to analyze the interactions among these important factors. The CART analysis highlighted license type, helmet usage, passenger age, and pedestrian clothing color as the most important factors affecting injury severity. The relative importance of these variables varied across user groups (pedestrians, vehicle occupants, and motorcyclists), and also factors such as lighting conditions, road geometry, and land use demonstrated significant effects across most models. The Bayesian network analysis further revealed that motorcyclists without a valid license or helmet, especially those aged 16 to 25, faced the highest risks of severe injury or fatality. Vulnerable users, including children and the elderly, were also more likely to experience fatal injuries when not wearing helmets. Additionally, elderly pedestrians wearing dark clothing were more likely to experience severe outcomes due to reduced visibility and delayed driver reaction times. These findings provide valuable insights for designing targeted strategies to reduce injuries and fatalities in urban traffic crashes.
Keywords
Injury Severity
Urban Areas
Road Users
Classification and Regression Trees (CART)
Bayesian Network Model
-Abay, K. A., Paleti, R., & Bhat, C. R. (2013). The joint analysis of injury severity of drivers in two-vehicle crashes accommodating seat belt use endogeneity. Transportation Research Part B: Methodological, 50, 74-89.
-Alkheder, S., AlRukaibi, F., & Aiash, A. (2020). Risk analysis of traffic accidents’ severities: An application of three data mining models. ISA Transactions, 106, 213-220.
-Araujo, M., Illanes, E., Chapman, E., & Rodrigues, E. (2017). Effectiveness of interventions to prevent motorcycle injuries: systematic review of the literature. International Journal of Injury Control and Safety Promotion, 24(3), 406-422.
-Arefkhani, H., Besharati, M. M., Azizi Bondarabadi, M., & Tavakoli Kashani, A. (2021). How does the incompatibility of different vehicle types affect the odds of driver injury? Journal of Transportation Safety & Security, 13(8), 860-876.
-Bank, W. (2020). Guide for Road Safety Opportunities and Challenges: Low and Middle Income Country Profiles.
-Beanland, V., Fitzharris, M., Young, K. L., & Lenné, M. G. (2013). Driver inattention and driver distraction in serious casualty crashes: Data from the Australian National Crash In-depth Study. Accident Analysis & Prevention, 54, 99-107.
-Borg, A., Bjelland, H., & Njå, O. (2014). Reflections on Bayesian Network models for road tunnel safety design: A case study from Norway. Tunnelling and Underground Space Technology, 43, 300-314.
-Breen, J. M., Næss, P. A., Hansen, T. B., Gaarder, C., & Stray-Pedersen, A. (2020). Serious motor vehicle collisions involving young drivers on Norwegian roads 2013–2016: Speeding and driver-related errors are the main challenge. Traffic Injury Prevention, 21(6), 382-388.
-Breiman, L. (2017). Classification and regression trees. Routledge.
-Cabrera-Arnau, C., Prieto Curiel, R., & Bishop, S. R. (2020). Uncovering the behaviour of road accidents in urban areas. Royal Society Open Science, 7(4), 191739.
-Celik, A. K., & Oktay, E. (2014). A multinomial logit analysis of risk factors influencing road traffic injury severities in the Erzurum and Kars Provinces of Turkey. Accident Analysis & Prevention, 72, 66-77.
-Chang, L.-Y., & Wang, H.-W. (2006). Analysis of traffic injury severity: An application of non-parametric classification tree techniques. Accident Analysis & Prevention, 38(5), 1019-1027.
-Chen, C., Zhang, G., Tarefder, R., Ma, J., Wei, H., & Guan, H. (2015). A multinomial logit model-Bayesian network hybrid approach for driver injury severity analyses in rear-end crashes. Accident Analysis & Prevention, 80, 76-88.
-Chu, H.-C. (2014). Assessing factors causing severe injuries in crashes of high-deck buses in long-distance driving on freeways. Accident Analysis & Prevention, 62, 130-136.
-Connor, J., Norton, R., Ameratunga, S., Robinson, E., Civil, I., Dunn, R., Bailey, J., & Jackson, R. (2002). Driver sleepiness and risk of serious injury to car occupants: population based case control study. Bmj, 324(7346), 1125.
-Copsey, N., Drupsteen, L., van Kampen, J., Kuijt-Evers, L., Schmitz-Felten, E., & Verjans, M. (2010) .A review of accidents and injuries to road transport drivers.
-Faso, B. (2019). Institute for Health Metrics and Evaluation. Institute for Health Metrics and Evaluation.
-Gregoriades, A., & Mouskos, K. C. (2013). Black spots identification through a Bayesian Networks quantification of accident risk index. Transportation Research Part C: Emerging Technologies, 28, 28-43.
-Hagel, B. E., Ruest, N., Morgunov, N., Embree, T., Couperthwaite, A. B., Voaklander, D., & Rowe, B. H. (2012). Do visibility aids reduce the risk of motor-vehicle injury in bicyclists? Injury Prevention, 18(Suppl 1), A36-A37.
-Haleem, K., & Gan, A. (2013). Effect of driver’s age and side of impact on crash severity along urban freeways: A mixed logit approach. Journal of Safety Research, 46, 67-76.
-Hänninen, M. (2014). Bayesian networks for maritime traffic accident prevention: Benefits and challenges. Accident Analysis & Prevention, 73, 305-312.
-Hossain, M., & Muromachi, Y. (2012). A Bayesian network based framework for real-time crash prediction on the basic freeway segments of urban expressways. Accident Analysis & Prevention, 45, 373-381.
-Høye, A. (2020). Speeding and impaired driving in fatal crashes—Results from in-depth investigations. Traffic Injury Prevention, 21(7),425-430.
-Kashani, A. T., & Mohaymany, A. S. (2011). Analysis of the traffic injury severity on two-lane, two-way rural roads based on classification tree models. Safety Science, 49(10), 1314-1320.
-Khattak, A. J., Ahmad, N., Wali, B., & Dumbaugh, E. (2021). A taxonomy of driving errors and violations: Evidence from the naturalistic driving study. Accident Analysis & Prevention, 151, 105873.
-Khosbayar, A., Valluru, J., & Huang, B. (2021). Multi-rate Gaussian Bayesian network soft sensor development with noisy input and missing data. Journal of Process Control, 105, 48-61.
-Kurgan, R. W. S. L. A., Cios, K. J., & Pedrycz, W. (2007). Data Mining: A Knowledge Discovery Approach. Springer.
-Lee, C., & Abdel-Aty, M. (2008). Presence of passengers: does it increase or reduce driver's crash potential? Accident Analysis & Prevention, 40(5), 1703-1712.
-Mbakwe, A. C., Saka, A. A., Choi, K., & Lee, Y. J. (2016). Alternative method of highway traffic safety analysis for developing countries using delphi technique and Bayesian network. Accident Analysis & Prevention, 93, 135-146.
-Mujalli, R. O., & De Oña, J. (2011). A method for simplifying the analysis of traffic accidents injury severity on two-lane highways using Bayesian networks. Journal of Safety Research, 42(5), 317-326.
-Olowosegun, A., Babajide, N., Akintola, A., Fountas, G., & Fonzone, A. (2022). Analysis of pedestrian accident injury-severities at road junctions and crossings using an advanced random parameter modelling framework: The case of Scotland. Accident Analysis & Prevention, 169, 106610.
-Pande, A., & Abdel-Aty, M. (2006). Assessment of freeway traffic parameters leading to lane-change related collisions. Accident Analysis & Prevention, 38(5), 936-948.
-Patil, S., Geedipally, S. R., & Lord, D. (2012). Analysis of crash severities using nested logit model—accounting for the underreporting of crashes. Accident Analysis & Prevention, 45, 646-653.
-Razzaghi, A., Soori, H., Kavousi, A., Abadi, A., & Khosravi, A. (2019). Factors with the highest impact on road traffic deaths in Iran; an ecological study. Archives of Academic Emergency Medicine, 7(1).
-Savolainen, P., & Mannering, F. (2007). Probabilistic models of motorcyclists’ injury severities in single-and multi-vehicle crashes. Accident Analysis &  Prevention, 39(5),955-963.
-Shaon, M. R. R., Qin, X., Chen, Z., & Zhang, J. (2018). Exploration of contributing factors related to driver errors on highway segments. Transportation Research Record, 2672(38), 22-34.
-Su, J., & Zhang, H. (2006). Full Bayesian network classifiers. Proceedings of the 23rd international conference on Machine learning,
-Ulak, M. B., Ozguven, E. E., Vanli, O. A., Dulebenets, M. A., & Spainhour, L. (2018). Multivariate random parameter Tobit modeling of crashes involving aging drivers, passengers, bicyclists, and pedestrians: Spatiotemporal variations. Accident Analysis & Prevention, 121, 1-13.
-Vollrath, M., Meilinger, T., & Krüger, H.-P. (2002). How the presence of passengers influences the risk of a collision with another vehicle. Accident Analysis & Prevention, 34(5), 649-654.
-Wang, K., & Qin, X. (2015). Exploring driver error at intersections: key contributors and solutions. Transportation Research Record, 2514(1), 1-9.
-Williamson, A., Friswell, R., Olivier, J., & Grzebieta, R. (2014). Are drivers aware of sleepiness and increasing crash risk while driving? Accident Analysis & Prevention, 70, 225-234.
-Wood, J. M., Tyrrell, R. A., & Carberry, T. P. (2003). Pedestrian visibility at night: Effects of pedestrian clothing, driver age, and headlamp beam setting. TRB 2003 Annual Meeting.
-Wu, Q., Chen, F., Zhang, G., Liu, X. C., Wang, H., & Bogus, S. M. (2014). Mixed logit model-based driver injury severity investigations in single-and multi-vehicle crashes on rural two-lane highways. Accident Analysis & Prevention, 72, 105-115.
-Wu, Q., Zhang, G., Ci, Y., Wu, L., Tarefder, R. A., & Alcántara, A. D. (2016). Exploratory multinomial logit model–based driver injury severity analyses for teenage and adult drivers in intersection-related crashes. Traffic Injury Prevention, 17(4), 413-422.
-Yadav, A. K., & Velaga, N. R. (2020). An investigation on the risk factors associated with driving errors under the influence of alcohol using structural equation modeling. Traffic Injury Prevention, 21(4), 288-294.
-Zajac, S. S., & Ivan, J. N. (2003). Factors influencing injury severity of motor vehicle–crossing pedestrian crashes in rural Connecticut. Accident Analysis & Prevention, 35(3), 369-379.