A Comprehensive Review of Machine Learning and Explainable AI Approaches for Road Accident Severity Prediction

References

[1] S. Ahmed et al., “Comparative Study of Machine Learning Algorithms for Accident Severity Prediction,” IEEE IUCC, 2021.

[2] U. Gupta et al., “Hotspot Analysis and Severity Prediction Using Machine Learning,” IEEE Conference, 2022.

[3] R. Kumar et al., “Deep Learning-Driven Accident Severity Prediction,” IEEE, 2025.

[4] V. Datta et al., “ML-Powered Web Application for Accident Severity Prediction,” Conference Proceedings, 2023.

[5] D. Dinesh, “Real-Time Accident Prediction System Using Deep Neural Networks,” Conference Proceedings, 2023.

[6] R. Shafique et al., “AV Sensor-Related Accident Severity Prediction Using Ensemble Learning,” IEEE Access, 2024.

[7] J. A. Sowdagur et al., “Artificial Neural Network for Accident Severity Prediction,” Conference Proceedings, 2020.

[8] M. Evin et al., “Alcohol Functional State Detection Using Machine Learning,” IEEE BIBM, 2018.

[9] K. Kim and Y. Lim, “Interpretable Maritime Accident Prediction Using Explainable AI,” IEEE Access, 2022.

[10] N. Kılıç et al., “Driver Injury Severity Prediction Using SMOTE-ENN and Random Forest,” Conference Proceedings, 2023.

[11] M. Mishra et al., “Spatio-Temporal Accident Count Prediction Using Machine Learning,” Conference Proceedings, 2024.

[12] K. Hussain et al., “Passenger Safety Enhancement Using Machine Learning Techniques,” IEEE SENNET, 2025.

[13] R. Mynavathi et al., “Machine Learning-Based Accident Severity Prediction with Explainable AI,” Conference Proceedings, 2023.

[14] K. Katoch et al., “Machine Learning-Based Classification of Road Accident Severity in India,” Conference Proceedings, 2023.

[15] N. Srivastava et al., “Unraveling Road Accident Risk Prediction Models With Explainable AI,” IEEE Transactions on Computational Social Systems, 2025.

[16] WHO, “Global Status Report on Road Safety,” World Health Organization, 2023.

[17] Y. LeCun, Y. Bengio, and G. Hinton, “Deep Learning,” Nature, vol. 521, no. 7553, pp. 436–444, 2015.

[18] L. Breiman, “Random Forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001.

[19] C. Cortes and V. Vapnik, “Support-Vector Networks,” Machine Learning, vol. 20, pp. 273–297, 1995.

[20] S. M. Lundberg and S.-I. Lee, “A Unified Approach to Interpreting Model Predictions,” Advances in Neural Information Processing Systems, 2017.

[21] M. T. Ribeiro, S. Singh, and C. Guestrin, “Why Should I Trust You? Explaining the Predictions of Any Classifier,” KDD Conference, 2016.

[22] T. Chen and C. Guestrin, “XGBoost: A Scalable Tree Boosting System,” KDD Conference, 2016.

[23] D. Silver et al., “Mastering the Game of Go with Deep Neural Networks and Tree Search,” Nature, 2016.

[24] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. MIT Press, 2016.

[25] J. Schmidhuber, “Deep Learning in Neural Networks: An Overview,” Neural Networks, vol. 61, pp. 85–117, 2015.

@article{1717760,
      author = {Shikha Patel, Dr. D. Ganesh},
      title = {A Comprehensive Review of Machine Learning and Explainable AI Approaches for Road Accident Severity Prediction},
      journal = {Iconic Research And Engineering Journals},
      year = {2026},
      volume = {9},
      number = {11},
      pages = {1642-1646},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1717760.pdf},
      abstract = {Road traffic accidents continue to be one of the major causes of injuries and fatalities across the globe, leading to severe social and economic consequences. In recent years, advancements in artificial intelligence have encouraged the use of machine learning (ML) and deep learning techniques to analyze accident data and predict accident severity. A variety of predictive approaches, including Random Forest, Neural Networks, Support Vector Machines, and deep learning architectures, have been explored to improve accident severity classification. Despite these developments, many existing studies face challenges such as limited dataset sizes, poor model interpretability, class imbalance problems, and lack of real-time implementation. Moreover, the transparency of predictive models has become an essential requirement for their practical use in transportation safety systems. This study provides a comprehensive review of fifteen recent research works focusing on accident severity prediction, hotspot identification, driver behavior analysis, and explainable artificial intelligence (XAI). The research compares different methodologies, datasets, and performance outcomes in order to highlight current research trends and identify gaps in the literature. Based on this analysis, a conceptual framework integrating machine learning, deep learning, and explainable AI techniques is proposed to enhance prediction accuracy and model interpretability. The proposed approach aims to support intelligent transportation systems and assist decision-makers in improving road safety strategies.},
      keywords = {Machine Learning, Accident Severity Prediction, Explainable Artificial Intelligence, Deep Learning, Road Safety, Random Forest},
      month = {May},
      doi = {https://doi.org/10.64388/IREV9I11-1717760}
  }