Risk-Aware Explainable Artificial Intelligence for City-Scale Injury Severity Prediction
Main Article Content
Abstract
The rapid expansion of urban environments has precipitated a corresponding increase in traffic-related incidents, making city-scale injury severity prediction a critical priority for public health and urban planning. While conventional predictive models often achieve high aggregate accuracy, they frequently fail to adequately penalize the misclassification of severe injuries, which represent a statistical minority but carry the highest societal and economic costs. Furthermore, the deployment of advanced machine learning models in municipal governance is consistently hindered by their lack of transparency, rendering them unsuitable for high-stakes decision-making. This paper proposes a comprehensive framework for a risk-aware, explainable artificial intelligence approach tailored to city-scale injury severity prediction. By integrating asymmetric cost-sensitive learning algorithms with post-hoc interpretability mechanisms, the proposed methodology simultaneously addresses class imbalance and the black-box nature of contemporary predictive systems. Through an extensive theoretical and analytical exploration, this research demonstrates how risk-aware loss formulations prioritize the identification of critical incidents without catastrophically degrading overall model performance. Concurrently, the integration of local and global explainability methods provides urban planners and emergency responders with actionable, transparent insights into the underlying causative factors of severe accidents. The findings advocate for a paradigm shift in urban predictive analytics, moving beyond pure predictive accuracy toward systems that are both ethically aligned with public safety priorities and transparent enough to justify policy interventions
Downloads
Article Details
Section
This work is licensed under a Creative Commons Attribution 4.0 International License.
-
All published articles are open access, with copyright shared between the authors and the journal. The journal retains the exclusive right to first publication and identifies itself as original publisher.
-
Articles are made available under a Creative Commons CC BY‑NC‑ND 4.0 license, permitting users to copy and distribute the content for non‑commercial purposes only, without modification, provided proper credit is given to authors and JCPHS.
-
Redistribution or reuse must preserve the full citation details and include a link to the license. No derivatives, adaptations, or commercial uses are permitted without prior written permission.
References
1. Chu, Y. B., Li, J., Jia, P., Cui, J., Zhang, R., Kang, X., ... & Zhang, S. (2021). Irf1-and Egr1-activated transcription plays a key role in macrophage polarization: A multiomics sequencing study with partial validation. International Immunopharmacology, 99, 108072.
2. Zhu, Di, et al. "RaX-Crash: A Resource Efficient and Explainable Small Model Pipeline with an Application to City Scale Injury Severity Prediction." arXiv preprint arXiv:2512.07848 (2025).
3. Qu, W., Wang, J., Gong, Y., Huang, X., & Xiao, L. (2025). An end-to-end robust point cloud semantic segmentation network with single-step conditional diffusion models. In Proceedings of the Computer Vision and Pattern Recognition Conference (pp. 27325-27335).
4. Wu, Y., Ren, Y., Wu, D., Xirasagar, S., & Johnson, J. (2022, June). Using D-dimer as a Biomarker to Predict COVID-19 Disease Severity from Clinical Data of Hospitalized Patients: A Machine Learning Approach. In 2022 IEEE 10th International Conference on Healthcare Informatics (ICHI) (pp. 664-668). IEEE.
5. Rajkomar, A., Oren, E., Chen, K., Dai, A. M., Hajaj, N., Hardt, M., et al. (2018). Scalable and accurate deep learning with electronic health records. NPJ Digital Medicine, 1, 18.
6. Estrada‐Valbuena, J. J., Li, C., Parra‐Giraldo, C. M., & Martínez‐López, R. (2026). The Emerging Role of Microbial Extracellular Vesicles in Neuroinflammation and Neurodegeneration. Medicine Bulletin, 2(2), 231-238.
7. Bagheri, Mahdi, et al. "An MRI Atlas of the Human Fetal Brain: Reference and Segmentation Tools for Fetal Brain MRI Analysis." ArXiv (2025): arXiv-2508.
8. Kamal, T., Wenhong, T., Guo, J., Shafiq, M., Shuaihong, J., & Xue, R. (2026). Adaptive Probabilistic Transformer for Medical Image Segmentation. Expert Systems with Applications, 131948.
9. Zhao, H., Gu, J., Wang, S., Lu, T., Zhang, X., Wu, Z., ... & Jiang, Y. G. (2026). LSTD: Long Short-Term Temporal Diffusion for Video Generation. IEEE Transactions on Multimedia.
10. Dong, J., Zhang, C., Qu, X., Ma, Z., Koniusz, P., & Ong, Y. S. (2026). Robust superalignment: Weak-to-strong robustness generalization for vision-language models. Advances in Neural Information Processing Systems, 38, 18345-18377.
11. Wu, Y., Liang, Y., Liang, J., Sun, W., Zhang, Q., & Li, M. Y. (2026). Systematic Deciphering of ATBC Nephrotoxicity Mechanisms via Machine Learning and Single‐Cell Analysis. Medicine Bulletin.
12. Lei, C., Tao, X., & Xiao, Y. (2023, May). Dietary Iodine intake and related factors among secondary school students in Macao. In Healthcare (Vol. 11, No. 10, p. 1472). MDPI.
13. Dong, J., Liu, J., Qu, X., & Ong, Y. S. (2025). Confound from All Sides, Distill with Resilience: Multi-Objective Adversarial Paths to Zero-Shot Robustness. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 624-634).
14. Xie, C., Zhu, D., Wang, Z., Zhang, H., & Wei, Z. (2026). Explainable AI for Mental Health Detection from Social Media: A Comparative Study of Traditional Machine Learning and a Large Language Model. Available at SSRN 6429778.
15. Cai, Lie, et al. "Deep learning model for breast shear wave elastography to improve breast cancer diagnosis (INSPiRED 006): An international, multicenter analysis." Journal of Clinical Oncology 43.32 (2025): 3482-3493.
16. Ren, Y., Wu, D., & Lopez–De Fede, A. (2022, June). Identification and Prediction of Low-Birthweight Baby Outcomes and Mom Risk Factors. In 2022 IEEE 10th International Conference on Healthcare Informatics (ICHI) (pp. 01-02). IEEE.
17. Dong, J., Koniusz, P., Feng, L., Zhang, Y., Zhu, H., Liu, W., ... & Ong, Y. S. (2025). Robustifying zero-shot vision language models by subspaces alignment. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 21037-21047).
18. Song, S., Tang, Y., & Qin, R. (2025). Synthetic Data Matters: Re-training with Geo-typical Synthetic Labels for Building Detection. IEEE Transactions on Geoscience and Remote Sensing.
19. Yao, Y., Li, Y., Zheng, S., & Zhu, T. (2025). MSA-TransUNet: A Multi-Scale Attention Enhanced Transformer-UNet Architecture for Accurate Vessel Segmentation and Visualization in Medical Imaging. Journal of Medicine and Life Sciences, 1(4), 48-57.
20. Xie, C., Zhu, D., Wang, Z., Zhang, H., & Wei, Z. (2026). Compliance-Aware Discharge Agent for Auditable ICU Discharge Planning: A Pilot Feasibility Study Using Structured eICU Records. Available at SSRN 6429758.
21. Tao, X., Chen, D., Liang, R., Zhang, X., Yu, X., Chung, S., ... & Xiao, Y. (2021). A comparative study on knowledge towards COVID-19 prevention among undergraduate students in Macao and Zhuhai, China. PeerJ, 9, e11833.
22. Ren, Y., Wu, D., Tong Ph D, Y., Lopez-De Fede Ph D, A., & Gareau, S. J. (2024). Benchmarking Machine Learning Models to Predict Low Birthweight Baby Outcomes and Identify Associated Risk Factors from an Extremely Unbalanced Large-Scale Dataset. Women's Health Issues, 34(72), 79.
23. Xu, H., Ge, J., & Ou, Y. (2026). DentaScope-AI: A Real-Time k-mer–Driven CNN-Attention Framework for Rapid Pathogen Identification and Virulence Prediction in Endodontic Infections Using Nanopore Sequencing. Frontiers in Healthcare Technology, 3(1), 112-122.
24. Yu, X., Li, J., Wang, J., Wang, Y., Li, S., Ma, X., ... & Wang, H. (2026). Prediction of risk of hearing loss by industry noise from cross-sectional and longitudinal data. Communications Medicine.
25. Guo, Y., Sekiguchi, Y., Zeng, W., Ebihara, S., Owaki, D., & Hayashibe, M. (2025). Physics-informed learning framework for lower limb kinematic prediction with sparse sensors and its application in chronic stroke. IEEE Transactions on Neural Systems and Rehabilitation Engineering.
26. Zhang, W., Zhu, J., Zhang, Y., Zhang, X., Dong, Y., Yu, X., ... & Shang, A. (2026). Development of a clinically applicable prediction tool for lymph node metastasis in papillary thyroid carcinoma using lasso-logistic regression. BMC cancer.
27. Lv, Qi, et al. "F1: A vision-language-action model bridging understanding and generation to actions." arXiv preprint arXiv:2509.06951 (2025).
28. Ding, S., Yu, X., Wang, Q., Luo, P., Li, H., Li, Z., ... & Zhang, C. (2025). Multifunctional hydrogel sensors with dynamic covalent networks for machine learning-assisted Parkinson's disease diagnosis and encrypted human-computer interaction. Materials Today Bio, 102524.
29. Dong, J., Chen, J., Xie, X., Lai, J., & Chen, H. (2024). Survey on adversarial attack and defense for medical image analysis: Methods and challenges. ACM Computing Surveys, 57(3), 1-38.