Multi-Scale Spatio-Temporal Transformer Network for Intelligent Healthcare and Transportation Systems: A Generative AI Approach

Abstract

Integrating healthcare systems with intelligent transportation networks represents a critical frontier in modern urban infrastructure, where efficient resource allocation and timely service delivery can significantly impact patient outcomes. However, current approaches often fail to capture the complex interplay between healthcare facility accessibility and transportation dynamics, particularly during emergencies. Additionally, the temporal dependencies in healthcare service delivery follow strict sequential patterns that significantly influence both routine operations and emergency response effectiveness. To address these challenges, we propose a multi-scale spatio-temporal transformer network for healthcare and transportation (MST-HT) that leverages generative AI capabilities. Our model employs multiple specialised transformer networks to model different spatial scales, capturing hidden dependencies while using graph convolutional networks to learn static infrastructure features. The architecture incorporates healthcare district patterns, emergency response corridors and facility distributions through a novel gating mechanism that adaptively combines features based on their predictive importance. The model maintains awareness of critical service delivery patterns by embedding healthcare-specific temporal position information while optimising resource allocation. Experiments on real-world datasets demonstrate MST-HT's superior performance, achieving a 15.7% reduction in emergency response times and a 23.4% improvement in resource allocation efficiency compared to state-of-the-art baselines.

Keywords

artificial inteligence / medical applications / transforms / transportation

Funding

This work was supported by The Applied Basic Research Program Project of the Department of Science and Technology of Liaoning Province under Grant 2025JH2/101330069.

Conflicts of Interest

The authors declare no conflicts of interest.

Data Availability Statement

Data available on request from the authors.

References

[1] A. K. Singh, R. Pamula, N. Akhter, et al., Intelligent Transportation System for Automated Medical Services During Pandemic,” Future Generation Computer Systems 163 (September 2024): 107515, https://doi.org/10.1016/j.future.2024.107515.

[2] X. X. Wang, J. J. Li, L. L. Fan, Y. T. Wang, and Y. K. Li, “Advancing Vehicular Healthcare: The DAO-Based Parallel Maintenance for Intelligent Vehicles,” IEEE Transactions on Intelligent Vehicles 8, no. 12 (December 2023): 4671-4673, https://doi.org/10.1109/tiv. 2023.3341855.

[3] R. Mukiri and V. B. Burra, “A Novel Vision Transformer Model for Rumor Prediction in COVID-19 Data CT Images,” Journal of Intelligent and Fuzzy Systems 46, no. 2 (April 2024): 3635-3648, https://doi.org/10.3233/jifs-236842.

[4] T. Liu and F. Sun, “Self-Aligning Multi-Modal Transformer for Oropharyngeal Swab Point Localization,” Tsinghua Science and Technology 29, no. 4 (August 2024): 1082-1091, https://doi.org/10.26599/tst.2023.9010070.

[5] J. H. Lv, B. G. Kim, B. D. Parameshachari, A. Slowik, and K. Q. Li, “Large Model-Driven Hyperscale Healthcare Data Fusion Analysis in Complex Multi-Sensors,” Information Fusion 115 (March 2025): 102780, https://doi.org/10.1016/j.inffus.2024.102780.

[6] G. Mani, J. K. Viswanadhapalli, and A. A. Stonier, “Prediction and Forecasting of Air Quality Index in Chennai Using Regression and ARIMA Time Series Models,” Journal of Engineering Research 10, no. 2A (June 2022): 179-194, https://doi.org/10.36909/jer.10253.

[7] S. S. Pei, C. H. Zhai, Z. Q. Wang, K. Z. Liu, and J. Hu, “Resilience Assessment of the Interdependent Transportation-Healthcare System During Emergency Response,” Structure and Infrastructure Engineering 20, no. 9 (September 2024): 1307-1321, https://doi.org/10.1080/15732479.2022.2136719.

[8] S. S. Pei, C. H. Zhai, J. Hu, Z. Q. Wang, and L. L. Xie, “Resilience Assessment and Enhancement of Interdependent Transportation-Healthcare System: A Spatial Accessibility Approach,” Transportation Research Part D: Transport and Environment 128 (March 2024): 104090, https://doi.org/10.1016/j.trd.2024.104090.

[9] H. D. Thai and J. H. Huh, “Optimizing Patient Transportation by Applying Cloud Computing and Big Data Analysis,” Journal of Supercomputing 78, no. 16 (November 2022): 18061-18090, https://doi.org/10.1007/s11227-022-04576-3.

[10] Z. Y. Pan, W. T. Zhang, Y. X. Liang, et al., Spatio-Temporal Meta Learning for Urban Traffic Prediction,” IEEE Transactions on Knowledge and Data Engineering 34, no. 3 (March 2022): 1462-1476, https://doi.org/10.1109/tkde.2020.2995855.

[11] Y. Guan, P. Wen, J. Li, J. Zhang, and X. Xie, “Deep Learning Blockchain Integration Framework for Ureteropelvic Junction Obstruction Diagnosis Using Ultrasound Images,” Tsinghua Science and Technology 29, no. 1 (February 2024): 1-12, https://doi.org/10.26599/tst.2022.9010016.

[12] X. Y. Li, Y. S. Gong, W. Liu, Y. L. Yin, Y. Zheng, and L. Q. Nie, “Dual-Track Spatio-Temporal Learning for Urban Flow Prediction With Adaptive Normalization,” Artificial Intelligence 328 (March 2024): 104065, https://doi.org/10.1016/j.artint.2024.104065.

[13] P. F. de Araujo, M. Naili, G. Kaddoum, E. T. Fapi, and Z. W. Zhu, “Unsupervised GAN-Based Intrusion Detection System Using Temporal Convolutional Networks and Self-Attention,” IEEE Transactions on Network and Service Management 20, no. 4 (December 2023): 4951-4963, https://doi.org/10.1109/TNSM.2023.3260039.

[14] S. Chandra, P. K. S. Prakash, S. Samanta, and S. Chilukuri, “ClinicalGAN: Powering Patient Monitoring in Clinical Trials With Patient Digital Twins,” Scientific Reports 14, no. 1 (May 2024): 12236, https://doi.org/10.1038/s41598-024-62567-1.

[15] X. X. Ta, Z. H. Liu, X. Hu, L. Yu, L. L. Sun, and B. W. Du, “Adaptive Spatio-Temporal Graph Neural Network for Traffic Forecasting,” Knowledge-Based Systems 242 (April 2022): 108199, https://doi.org/10.1016/j.knosys.2022.108199.

[16] Y. J. Li, Y. Wu, M. C. Sun, B. Yang, and Y. Wang, “Learning Continuous Dynamic Network Representation With Transformer-Based Temporal Graph Neural Network,” Information Sciences 649 (November 2023): 119596, https://doi.org/10.1016/j.ins.2023.119596.

[17] J. J. Tao, Z. Chen, Z. C. Sun, et al., Seg-Road: A Segmentation Network for Road Extraction Based on Transformer and CNN With Connectivity Structures,” Remote Sensing 15, no. 6 (March 2023): 1602, https://doi.org/10.3390/rs15061602.

[18] T. Y. Zhao, Y. C. Tang, Q. M. Li, and J. Q. Wang, “Resilience-Oriented Network Reconfiguration Strategies for Community Emergency Medical Services,” Reliability Engineering & System Safety 231 (March 2023): 109029, https://doi.org/10.1016/j.ress.2022.109029.

[19] C. Oh, Y. Chun, and H. Kim, “Location Planning of Emergency Medical Facilities Using the p-Dispersed-Median Modeling Approach ,” ISPRS International Journal of Geo-Information 12, no. 12 (December 2023): 497, https://doi.org/10.3390/ijgi12120497.

[20] A. Ali, I. Ullah, M. Shabaz, et al. , “A Resource-Aware Multi-Graph Neural Network for Urban Traffic Flow Prediction in Multi-Access Edge Computing Systems,” IEEE Transactions on Consumer Electronics 70, no. 4 (January 2025): 7252-7265, https://doi.org/10.1109/tce.2024.3439719.

[21] A. Ali, H. M. Y. Naeem, A. Sharafian, L. Qiu, Z. Z. Wu, and X. S. Bai, “Dynamic Multi-Graph Spatio-Temporal Learning for Citywide Traffic Flow Prediction in Transportation Systems,” Chaos, Solitons & Fractals 199, no. 3 (July 2025): 116898, https://doi.org/10.1016/j.chaos.2025.116898.

[22] X. S. Bai, W. S. Yan, and S. S. Ge, “An Attention-Driven Spatio-Temporal Deep Hybrid Neural Networks for Traffic Flow Prediction in Transportation Systems,” IEEE Transactions on Intelligent Transportation Systems 26, no. 9 (February 2025): 14154-14168, https://doi.org/10.1109/TITS.2025.3540852.

[23] X. S. Bai, M. Cao, W. S. Yan, S. S. Ge, and X. Y. Zhang, “Efficient Heuristic Algorithms for Single-Vehicle Task Planning With Precedence Constraints,” IEEE Transactions on Cybernetics 51, no. 12 (January 2022): 6274-6283, https://doi.org/10.1109/tcyb.2020.2974832.

[24] X. S. Bai, W. S. Yan, and S. S. Ge, “Distributed Task Assignment for Multiple Robots Under Limited Communication Range,” IEEE Transactions on Systems, Man, and Cybernetics: Office Systems 52, no. 7 (July 2022): 4259-4271, https://doi.org/10.1109/tsmc.2021.3094190.

[25] X. S. Bai, W. S. Yan, and S. S. Ge, “Efficient Task Assignment for Multiple Vehicles With Partially Unreachable Target Locations,” IEEE Internet of Things Journal 8, no. 5 (March 2021): 3730-3742, https://doi.org/10.1109/jiot.2020.3025797.

[26] A. Kowark, M. Felzen, S. Ziemann, et al., Telemedical Support for Prehospital Emergency Medical Service in Severe Emergencies: An Open-Label Randomised Non-Inferiority Clinical Trial,” Critical Care 27, no. 1 (June 2023): 256, https://doi.org/10.1186/s13054-023-04545-z.

[27] H. Myrskykari, T. Iirola, and H. Nordquist, “The Role of Emergency Medical Services in the Management of in-Hospital Emergencies: Causes and Outcomes of Emergency Calls-A Descriptive Retrospective Register-Based Study,” Australasian Emergency Care 27, no. 1 (March 2024): 42-48, https://doi.org/10.1016/j.auec.2023.07.007.

[28] T. L. Hoang and V. C. Ta, “Balancing Structure and Position Information in Graph Transformer Network With a Learnable Node,” Expert Systems With Applications 238 (March 2024): 122096, https://doi.org/10.1016/j.eswa.2023.122096.

[29] G. Eslami and F. Ghaderi, “A District-Centric Attention Mechanism Approach for Online Ride-Hailing Demand Forecasting,” IEEE Access 12 (October 2024): 141190-141197, https://doi.org/10.1109/access.2024.3411512.

[30] J. Afshar, A. H. Roudsari, and W. Lee, “Top-k Team Synergy Problem: Capturing Team Synergy Based on C3 ,” Information Sciences 589 (April 2022): 117-141, https://doi.org/10.1016/j.ins.2021.12.101.

[31] Y. J. Ma and R. L. Wang, “Relative-Position Embedding Based Spatially and Temporally Decoupled Transformer for Action Recognition,” Pattern Recognition 145 (January 2024): 109905, https://doi.org/10.1016/j.patcog.2023.109905.

[32] X. Y. Qi, W. J. Hu, B. S. Li, and K. Han, “STGNN-FAM: A Traffic Flow Prediction Model for Spatiotemporal Graph Networks Based on Fusion of Attention Mechanisms,” Journal of Advanced Transportation 2023 (May 2023): 8880530, https://doi.org/10.1155/2023/8880530.

[33] C. Ounoughi and S. Ben Yahia, “Sequence to Sequence Hybrid Bi-LSTM Model for Traffic Speed Prediction,” Expert Systems With Applications 236 (February 2024): 121325, https://doi.org/10.1016/j.eswa.2023.121325.

[34] X. D. Cui and H. Lv, “STEFT: Spatio-Temporal Embedding Fusion Transformer for Traffic Prediction,” Electronics 13, no. 19 (October 2024): 3816, https://doi.org/10.3390/electronics13193816.

[35] J. N. Xia, S. Z. Wang, X. Wang, M. Xia, K. Xie, and J. N. Cao, “Multi-View Bayesian Spatio-Temporal Graph Neural Networks for Reliable Traffic Flow Prediction,” International Journal of Machine Learning and Cybernetics 15, no. 1 (January 2024): 65-78, https://doi.org/10.1007/s13042-022-01689-2.

[36] S. L. Pu, L. Chu, J. C. Hu, S. B. Li, J. H. Li, and W. Sun, “Sggformer: Shifted Graph Convolutional Graph-Transformer for Traffic Prediction,” Sensors 22, no. 22 (November 2022): 9024, https://doi.org/10.3390/s22229024.

[37] W. J. Xiao and X. M. Wang, “Spatial-Temporal Dynamic Graph Convolutional Neural Network for Traffic Prediction,” IEEE Access 11 (October 2023): 97920-97929, https://doi.org/10.1109/access.2023.3312534.

[38] H. Yang, C. Jiang, Y. Song, W. D. Fan, Z. L. Deng, and X. K. Bai, “TARGCN: Temporal Attention Recurrent Graph Convolutional Neural Network for Traffic Prediction,” Complex & Intelligent Systems 10, no. 6 (August 2024): 8179-8196, https://doi.org/10.1007/s40747-024-01601-1.

[39] S. Y. Feng, S. Q. Wei, J. B. Zhang, et al., A Macro-Micro Spatio-Temporal Neural Network for Traffic Prediction,” Transportation Research Part C: Emerging Technologies 156 (November 2023): 104331, https://doi.org/10.1016/j.trc.2023.104331.