Author(s)

YiZhi Yin, YuBin Jian, JiaYi Tan, WeiZhong Xu^* 

Affiliation(s)

School of Civil Engineering, Southwest Jiaotong University Hope College, Sichuan 610400, Chengdu, China. 

Corresponding Author

WeiZhong Xu

ABSTRACT

Accurate prediction of the severity of road traffic accident injuries provides a foundation for accident prevention, emergency resource allocation, and response planning. As a result, the selection of traffic accident injury severity prediction models has garnered significant attention from both authorities and researchers. This paper aims to provide a comprehensive review of the research progress on traffic accident severity prediction models. It begins by reviewing relevant datasets and features used in severity prediction. Next, it summarizes various approaches and models in traffic accident severity prediction, including traditional statistical models and machine learning techniques. A comparative analysis of these models is then conducted. Finally, the paper discusses the key challenges in current research and explores future development trends, offering theoretical guidance for both researchers and practitioners. 

KEYWORDS

Traffic accidents; Road traffic injuries; Prediction models

CITE THIS PAPER

YiZhi Yin, YuBin Jian, JiaYi Tan, WeiZhong Xu. A literature survey of crash injury severity prediction. Journal of Computer Science and Electrical Engineering. 2025, 7(2): 1-11. DOI: https://doi.org/10.61784/jcsee3041.

REFERENCES

[1] World Health Organization. World health statistics 2024: Monitoring health for the SDGs, Sustainable Development Goals. World Health Organization, Geneva, 2024. https://www.who.int/data/gho/publications/worldhealth-statistics.

[2] Abdelwahab HT, Abdel-Aty MA. Development of artificial neural network models to predict driver injury severity in traffic accidents at signalized intersections. Transportation Research Record, 2001, 1746(1): 6-13.

[3] Ahmadi A, Jahangiri A, Berardi V, et al. Crash severity analysis of rear-end crashes in California using statistical and machine learning classification methods. Journal of Transportation Safety & Security, 2020, 12(4): 522-546.

[4] Vajari MA, Aghabayk K, Sadeghian M, et al. A multinomial logit model of motorcycle crash severity at Australian intersections. Journal of Safety Research, 2024, 73: 17-24.

[5] Acevedo MA, Corrada-Bravo CJ, Corrada-Bravo H, et al. Automated classification of bird and amphibian calls using machine learning: A comparison of methods. Ecological Informatics, 2009, 4(4): 206-214.

[6] Al-Moqri T, Haijun X, Namahoro JP, et al. Exploiting machine learning algorithms for predicting crash injury severity in Yemen: Hospital case study. Applied and Computational Mathematics, 2020, 9(5): 155-164.

[7] Arhin SA, Gatiba A. Predicting crash injury severity at unsignalized intersections using support vector machines and na?ve Bayes classifiers. Transportation Safety and Environment, 2020, 2(2): 120-132.

[8] Theofilatos A, Chen C, Antoniou C. Comparing machine learning and deep learning methods for real-time crash prediction. Transportation Research Record, 2019, 2673(8): 169-178.

[9] Khalesian M, Furno A, Leclercq L. Improving deep-learning methods for area-based traffic demand prediction via hierarchical reconciliation. Transportation Research Part C: Emerging Technologies, 2024, 159: 104410.

[10] Wu Z. Deep learning with improved metaheuristic optimization for traffic flow prediction. Journal of Computer Science and Technology Studies, 2024, 6(4): 47-53.

[11] Li Y, Li P, Yan D, et al. Deep knowledge distillation: A self-mutual learning framework for traffic prediction. Expert Systems with Applications, 2024, 252: 124138.

[12] Jian F, Tian L, Yuqiang Q. Traffic accident prediction method based on multi-view spatial-temporal learning. Bulletin of the Polish Academy of Sciences: Technical Sciences. 2024, 72(6).

[13] Alhaek F, Li T, Rajeh TM, et al. Encoding global semantic and localized geographic spatial-temporal relations for traffic accident risk prediction. 2024.

[14] Gao X, Haworth J, Ilyankou I, et al. Sma-hyper: Spatiotemporal multi-view fusion hypergraph learning for traffic accident prediction. 2024. arXiv preprint arXiv:2407.17642. 2024.

[15] Trirat P, Yoon S, Lee J-G. Mg-tar: Multi-view graph convolutional networks for traffic accident risk prediction. IEEE Transactions on Intelligent Transportation Systems, 2023, 24(4): 3779-3794.

[16] Zhang D, Li J. Multi-view fusion neural network for traffic demand prediction. Information Sciences, 2023, 646: 119303.

[17] Ministry of Justice of the People's Republic of China. Standards for the Identification of the Degree of Human Injury. Tech. Rep. Announcement, Supreme People's Court Supreme People's Procuratorate Ministry of Public Security Ministry of State Security Ministry of Justice, Beijing. 2013.  https://www.moj.gov.cn/pub/sfbgw/zwxxgk/fdzdgknr/fdzdgknrtzwj/201908/t20190816_207509.html.

[18] Kashani AT, Mohaymany AS. Analysis of the traffic injury severity on two-lane, two-way rural roads based on classification tree models. Safety Science, 2011, 49(10): 1314-1320.

[19] De O?a J, Mujalli RO, Calvo FJ. Analysis of traffic accident injury severity on Spanish rural highways using Bayesian networks. Accident Analysis & Prevention, 2011, 43(1): 402-411.

[20] Haq MT, Zlatkovic M, Ksaibati K. Assessment of commercial truck driver injury severity based on truck configuration along a mountainous roadway using hierarchical Bayesian random intercept approach. Accident Analysis & Prevention, 2021, 162: 106392.

[21] Wang B, Lin Y, Guo S, et al. Gsnet: Learning spatial-temporal correlations from geographical and semantic aspects for traffic accident risk forecasting. In: Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 35: 4402-4409.

[22] Li Y, Yu R, Shahabi C, et al. Diffusion convolutional recurrent neural network: Data-driven traffic forecasting. 2017. arXiv preprint arXiv:1707.01926. 2017.

[23] Guo S, Lin Y, Wan H, et al. Learning dynamics and heterogeneity of spatial-temporal graph data for traffic forecasting. IEEE Transactions on Knowledge and Data Engineering, 2021, 34(11): 5415-5428.

[24] Xu Z, Lv Z, Li J, et al. A novel perspective on travel demand prediction considering natural environmental and socioeconomic factors. IEEE Intelligent Transportation Systems Magazine, 2022, 15(1): 136-159.

[25] Oeschger G, Carroll P, Caulfield B. Micromobility and public transport integration: The current state of knowledge. Transportation Research Part D: Transport and Environment, 2020, 89: 102628.

[26] Wu A, Nowozin S, Meeds E, et al. Deterministic variational inference for robust Bayesian neural networks. 2018. arXiv preprint arXiv:1810.03958. 2018.

[27] Selvaraj S, Ramani G. Classification of seating position specific patterns in road traffic accident data through data mining techniques. In: Second International Conference on Computer Applications, 2012.

[28] Wang J, Kong Y, Fu T. Expressway crash risk prediction using back propagation neural network: A brief investigation on safety resilience. Accident Analysis & Prevention, 2019, 124: 180-192.

[29] Mokhtarimousavi S, Anderson JC, Azizinamini A, et al. Improved support vector machine models for work zone crash injury severity prediction and analysis. Transportation Research Record: Journal of the Transportation Research Board, 2019, 2673(11): 680-692.

[30] Pervez A, Huang H, Lee J, et al. Factors affecting injury severity of crashes in freeway tunnel groups: A random parameter approach. Journal of Transportation Engineering, Part A: Systems, 2022.

[31] Prati G, Pietrantoni L, Fraboni F. Using data mining techniques to predict the severity of bicycle crashes. Accident Analysis and Prevention, 2017, 101: 44-54.

[32] Castro Y, Kim YJ. Data mining on road safety: Factor assessment on vehicle accidents using classification models. International Journal of Crashworthiness, 2016, 21(2): 104-111.

[33] Wei WWS. Time Series Analysis. Addison-Wesley, 2006.

[34] Box GEP, Jenkins GM, Reinsel GC. Time Series Analysis: Forecasting and Control. John Wiley & Sons, 1976.

[35] Hyndman RJ, Athanasopoulos G. Forecasting: Principles and Practice. OTexts, 2018.

[36] Lütkepohl H. New Introduction to Multiple Time Series Analysis. Springer, 2005.

[37] Lord D, Mannering F. The statistical analysis of crash-frequency data: A review and assessment of methodological alternatives. Transportation Research Part A: Policy and Practice, 2010, 44(5): 291-305.

[38] Ospina-Mateus H, Quintana Jiménez LA, Lopez-Valdes FJ, et al. Extraction of decision rules using genetic algorithms and simulated annealing for prediction of severity of traffic accidents by motorcyclists. Journal of Ambient Intelligence and Humanized Computing, 2021, 1: 3.

[39] Dong N, Huang H, Zheng L, et al. Support vector machine in crash prediction at the level of traffic analysis zones: Assessing the spatial proximity effects. Accident Analysis & Prevention, 2015, 82: 192-198.

[40] Lv Y, Tang S, Zhao H, et al. Real-time highway traffic accident prediction based on the k-nearest neighbor method. In: 2009 International Conference on Measuring Technology and Mechatronics Automation (ICMTMA '09). IEEE, 2009.

[41] Wang W, Wang Y, Kweon Y-J. Spatial-temporal graph convolutional networks for traffic flow forecasting. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(12): 7891-7903.

[42] Hochreiter S, Schmidhuber J. Long short-term memory. Neural Computation, 1997, 9(8): 1735-1780.

[43] Ioannou Y, Underwood J. A review of machine learning approaches to traffic prediction. IEEE Transactions on Intelligent Transportation Systems, 2019, 20(1): 337-350.

[44] Zhang D, Yan J, Polat K, et al. Multimodal joint prediction of traffic spatial-temporal data with graph sparse attention mechanism and bidirectional temporal convolutional network. Advanced Engineering Informatics, 2024, 62: 102533.

[45] Cui P, Yang X, Abdel-Aty M, et al. Advancing urban traffic accident forecasting through sparse spatio-temporal dynamic learning. Accident Analysis and Prevention, 2024, 200: 107564.

[46] Zhang W, Wang H, Zhang F. Spatio-temporal Fourier enhanced heterogeneous graph learning for traffic forecasting. Expert Systems with Applications, 2024, 241: 122766.

[47] Santos K, Dias JP, Amado C. A literature review of machine learning algorithms for crash injury severity prediction. Journal of Safety Research, 2022, 80: 254-269.

[48] Pearl J. The seven tools of causal inference, with reflections on machine learning. Communications of the ACM, 2019, 62(3): 54-60.

[49] Chen C, Antoniou C. Comparing machine learning and deep learning methods for real-time crash prediction. Transportation Research Record, 2019, 2673(8): 169-178.

[50] Kumar PB, Hariharan K. Time series traffic flow prediction with hyper-parameter optimized ARIMA models for intelligent transportation system. Journal of Scientific & Industrial Research, 2022, 81(4): 408-415.

[51] Sarkar A, Sarkar S. Comparative assessment between statistical and soft computing methods for accident severity classification. Journal of The Institution of Engineers (India) Series A, 2019, 101(1).

[52] Al-Ghamdi AS. Using logistic regression to estimate the influence of accident factors on accident severity. Accident Analysis & Prevention, 2002.

[53] Li Z, Liu P, Wang W, et al. A hybrid machine learning approach for crash prediction with imbalanced data. Accident Analysis & Prevention, 2021, 159: 106256.

[54] Abellán J, López G, Oa JD. Analysis of traffic accident severity using decision rules via decision trees. Expert Systems with Applications, 2013, 40(15): 6047-6054.

[55] A M M A, B K K. Analyzing injury severity of motorcycle at-fault crashes using machine learning techniques, decision tree and logistic regression models. International Journal of Transportation Science and Technology, 2020, 9(2): 89-99.

[56] Yang J, Han S, Chen Y. Prediction of traffic accident severity based on random forest. Journal of Advanced Transportation, 2023.

[57] Zhang J, Li Z, Pu Z, et al. Comparing prediction performance for crash injury severity among various machine learning and statistical methods. IEEE Access, 2018: 1-1.

[58] Milletari F, Navab N, Ahmadi SA. V-net: Fully convolutional neural networks for volumetric medical image segmentation. In: 2016 Fourth International Conference on 3D Vision (3DV). IEEE, 2016.

[59] Khan MN, Das A, Ahmed MM. Prediction of truck-involved crash severity on a rural mountainous freeway using transfer learning with ResNet-50 deep neural network. Journal of Transportation Engineering, Part A: Systems, 2024, 150(2): 04023131.

[60] Kunt MM, Aghayan I, Noii N. Prediction for traffic accident severity: Comparing the artificial neural network, genetic algorithm, combined genetic algorithm and pattern search methods. Transport, 2011, 26(4): 353-366.

[61] Wang H, Lian D, Liu W, et al. Powerful graph of graphs neural network for structured entity analysis. World Wide Web, 2022, 25(2): 609-629.

[62] Shi M, Tang Y, Zhu X, et al. Genetic-gnn: Evolutionary architecture search for graph neural networks. Knowledge-Based Systems, 2022, 247: 108752.

[63] Zhang Y, Zhao T, Gao S, et al. Incorporating multimodal context information into traffic speed forecasting through graph deep learning. International Journal of Geographical Information Science, 2023, 37(9): 1909-1935.

[64] Zhang X, Huang C, Xu Y, et al. Traffic flow forecasting with spatial-temporal graph diffusion network. In: Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 35: 15008-15015.

[65] He S, Luo Q, Du R, et al. Stgc-gnns: A gnn-based traffic prediction framework with a spatial-temporal granger causality graph. Physica A: Statistical Mechanics and its Applications, 2023, 623: 128913.

[66] Jia H, Yu Z, Chen Y, et al. Spatial-temporal multi-factor fusion graph neural network for traffic prediction. Applied Intelligence, 2024, 19: 54.

[67] Jin C, Ruan T, Wu D, et al. HetGAT: A heterogeneous graph attention network for freeway traffic speed prediction. Journal of Ambient Intelligence and Humanized Computing, 2021: 1-12.

[68] Qi J, Zhao Z, Tanin E, et al. A graph and attentive multi-path convolutional network for traffic prediction. IEEE Transactions on Knowledge and Data Engineering, 2022, 35.

[69] Jiang W, Xiao Y, Liu Y, et al. Bi-grcn: A spatio-temporal traffic flow prediction model based on graph neural network. Journal of Advanced Transportation, 2022, 2022(1): 5221362.

[70] Qi J, Zhao Z, Tanin E, et al. A graph and attentive multi-path convolutional network for traffic prediction. IEEE Transactions on Knowledge and Data Engineering, 2022, 35(7): 6548-6560.

[71] He S, Luo Q, Du R, et al. Stgc-gnns: A gnn-based traffic prediction framework with a spatial-temporal granger causality graph. Physica A: Statistical Mechanics and its Applications, 2023, 623: 128913.

[72] Zhang Z, Yang H, Yang X. A transfer learning-based LSTM for traffic flow prediction with missing data. Journal of Transportation Engineering, Part A: Systems, 2023, 149(10): 04023095.

[73] Li H, Zhang S, Li X, et al. Detectornet: Transformer-enhanced spatial temporal graph neural network for traffic prediction, 2021.

[74] de Dieu J, Gatesi, Bin S, et al. Analysis and modelling of the contributing factors associated with road traffic crashes in Rwanda. International Journal of Crashworthiness, 2024: 1-13.

[75] Chen Z, Li Y, Wang H, et al. Region-aware text-to-image generation via hard binding and soft refinement. 2024. arXiv preprint arXiv:2411.06558. 2024.

[76] John C, Milton, Venky N, et al. Highway accident severities and the mixed logit model: An exploratory empirical analysis. Accident Analysis & Prevention, 2008, 40(1): 260-266.

[77] Gopinath V, Prakash KP, Yallamandha C, et al. Traffic accidents analysis with respect to road users using data mining techniques.

[78] Yuan Y, Yang M, Guo Y, et al. Risk factors associated with truck-involved fatal crash severity: Analyzing their impact for different groups of truck drivers. Journal of Safety Research, 2020.

[79] Mokhtarimousavi S, Anderson JC, Azizinamini A, et al. Factors affecting injury severity in vehicle-pedestrian crashes: A day-of-week analysis using random parameter ordered response models and artificial neural networks. International Journal of Transportation Science and Technology, 2020, 9(2): 100-115.  https://www.sciencedirect.com/science/article/pii/S2046043020300034.

[80] Zhang J, Li Z, Pu Z, et al. Comparing prediction performance for crash injury severity among various machine learning and statistical methods. IEEE Access, 2018, 6: 60079-60087.

[81] Singh G, Sachdeva S, Pal M. Comparison of three parametric and machine learning approaches for modeling accident severity on non-urban sections of Indian highways. Advances in Transportation Studies, 2018, 45.

[82] Li Z, Liu P, Wang W, et al. Using support vector machine models for crash injury severity analysis. Accident Analysis & Prevention, 2012, 45: 478-486.

[83] Li J, Xu S, Guo J, et al. Explanatory prediction of injury severity in traffic incidents: A hybrid approach with latent class clustering and causal Bayesian network. 2023.

[84] Zou, X., & Yue, W. L. A bayesian network approach to causation analysis of road accidents using netica. Journal of advanced transportation, 2017(1), 2525481.

[85] De Ona J, Lopez G, Mujalli R, et al. Analysis of traffic accidents on rural highways using latent class clustering and Bayesian networks. Accident Analysis & Prevention, 2013, 51: 1-10.

[86] Jin C, Ruan T, Wu D, et al. Hetgat: A heterogeneous graph attention network for freeway traffic speed prediction. Journal of Ambient Intelligence and Humanized Computing, 2021: 1-12.

[87] Zhang Z, Li Y, Song H, et al. Multiple dynamic graph based traffic speed prediction method. Neurocomputing, 2021, 461: 109-117.

[88] Cui P, Yang X, Abdel-Aty M, et al. Advancing urban traffic accident forecasting through sparse spatio-temporal dynamic learning. Accident Analysis & Prevention, 2024, 200: 107564.

[89] Li P, Abdel-Aty M, Yuan J. Real-time crash risk prediction on arterials based on lstm-cnn. Accident Analysis & Prevention, 2020, 135: 105371.

[90] Wei Z, Zhuping Z, Lei L, et al. Identifying significant injury severity risk factors in traffic accidents based on the machine learning methods. CICTP 2019, 2019.

[91] Lee J, Yoon T, Kwon S, et al. Model evaluation for forecasting traffic accident severity in rainy seasons using machine learning algorithms: Seoul city study. Applied Sciences, 2019, 10(1): 129.

[92] Al-Moqri T, Haijun X, Namahoro JP, et al. Exploiting machine learning algorithms for predicting crash injury severity in Yemen: Hospital case study. Applied and Computational Mathematics, 2020, 9(5): 155-164.

[93] Santos K, Dias JP, Amado C. A literature review of machine learning algorithms for crash injury severity prediction. Journal of Safety Research, 2022, 80: 254-269.

[94] Yu B, Yin H, Zhu Z. Spatio-temporal graph convolutional networks: A deep learning framework for traffic forecasting. 2017. arXiv preprint arXiv:1709.04875. 2017.

[95] Zhang J, Zheng Y, Qi D. Deep spatio-temporal residual networks for citywide crowd flows prediction. In: Proceedings of the AAAI Conference on Artificial Intelligence, 2017, 31.