Abstract
Rehabilitation services are provided in various settings, including homes, schools, and clinics, leading to significant variations in data quality, regulation, terminology, and documentation. While wearable sensing, edge AI, and medical knowledge graphs offer complementary technological capabilities, current evidence does not suggest that simply combining them improves clinical outcomes. This paper proposes a conceptual, testable framework, rather than reporting completed human subject deployments or clinical trials. We synthesize published evidence from the fields of rehabilitation medicine, health informatics, and edge AI engineering to derive five design requirements that directly guide the proposed architecture. The contribution of this paper lies in the architectural blueprint, the source model, and the phased evaluation plan, rather than a validated treatment protocol. Future pre-registration studies are needed to test the clinical and technical effectiveness of this framework across different populations, settings, and devices.
References
[1] Fan, T., Zhou, X., He, P., Zhan, X., Zheng, P., Chen, R., ... & Huang, G. (2021). Effects of radial extracorporeal shock wave therapy on flexor spasticity of the upper limb in post-stroke patients: study protocol for a randomized controlled trial. Frontiers in neurology, 12, 712512.
[2] Fan, T., Zheng, P., Zhang, X., Gong, Z., Shi, Y., Wei, M., ... & Huang, G. (2025). Effects of exoskeleton rehabilitation robot training on neuroplasticity and lower limb motor function in patients with stroke. BMC neurology, 25(1), 193.
[3] Wang, J., Seo, J., Gong, Y., Ming-Fung, F. S., Hwang, S., & Khan, M. (2025). Sub-activity analysis by using wristband-type wearable health devices to measure construction workers’ physical demands. Journal of Civil Engineering and Management, 31(5), 516.
[4] Rotmensch, M., Halpern, Y., Tlimat, A., Horng, S., & Sontag, D. (2017). Learning a health knowledge graph from electronic medical records. Scientific reports, 7(1), 5994.
[5] Xu, T. (2025). A Study on the “Tiered-Gamification” Model for Language Rehabilitation Training in Children with Special Needs. Current Research in Medical Sciences, 4(5), 16-21.
[6] Wang, B., Qu, J., Li, X., Wang, C., & Bu, L. (2026). A personalized rehabilitation design method via knowledge graph-based multi-source data integration. Advanced Engineering Informatics, 69, 104005.
[7] He, T., Chen, Y., Wang, L., & Cheng, H. (2024). An expert-knowledge-based graph convolutional network for skeleton-based physical rehabilitation exercises assessment. IEEE transactions on neural systems and rehabilitation engineering, 32, 1916-1925.
[8] Alsheikhy, A. A., Shawly, T., Said, Y. E., Ahmed, H. E., & Alazzam, M. B. (2025). Developing machine learning models for personalized game-based stroke rehabilitation therapy in virtual reality. Alexandria Engineering Journal, 121, 358-369.
[9] Hao, Z. (2026). Low-Overhead Scheduling for Real-Time AI Workloads on Multi-Core Edge Chips. International Journal of Advance in Applied Science Research, 5(3), 15-25.
[10] Hao, Z. (2026). Dynamic Task Prioritization for Edge AI in Smart Cities: Balancing Latency and Energy Efficiency. Journal of Intelligence and Engineering Technology, 1(1), 60-69.
[11] Hao, Z., Yin, M., Xu, J., Liu, Z., & Chen, Y. (2026, March). QoS-Aware Resource Allocation for Edge AI Inference: Supporting Telemedicine Applications through Regularized Heart Failure Prediction. In 2026 IEEE 8th International Conference on Communications, Information System and Computer Engineering (CISCE) (pp. 477-480). IEEE.
[12] Hao, Z. (2026). Structure-Aware Deep Reinforcement Learning for Latency-Minimal Scheduling of Edge AI Inference on Heterogeneous Cores. Journal of Intelligence and Engineering Technology, 1(1), 50-59.
[13] Li, L., Wang, P., Yan, J., Wang, Y., Li, S., Jiang, J., ... & Liu, Y. (2020). Real-world data medical knowledge graph: construction and applications. Artificial intelligence in medicine, 103, 101817.
[14] Lebo, T., Sahoo, S., McGuinness, D., Belhajjame, K., Cheney, J., Corsar, D., ... & Zhao, J. (2013). Prov-o: The prov ontology.
[15] Rui, H. (2026). Theoretical Analysis on Standardization of Time-Based Moxibustion with Linggui Bafa for Intervention in Mild Cognitive Impairment: From the Perspectives of Time-Based Qi Transformation and Meridian Time Sequence. Insights in Social Science, 4(2), 102-113.
[16] Wei, M. (2026). Functional Testing for Return-to-Sport Decision-Making After Anterior Cruciate Ligament Reconstruction: An Updated Narrative Review. Current Research in Medical Sciences, 5(2), 34-42.
[17] Wei, M. (2026). A Review of Foot Strike Patterns and Injury Considerations in Recreational Endurance Runners. Studies in Sports Science and Physical Education, 4(1), 8-18.
[18] Huang, R. (2026). Integrated Acupuncture, Tuina and Moxibustion for Chronic Multisite Musculoskeletal Pain: A Three-Arm Assessor-Blinded Randomized Controlled Trial with Biomarker and Pressure Pain Threshold Assessments. Journal of Innovations in Medical Research, 5(2), 16-22.
[19] Wei, M. (2026). A Review of the Physiological Effects of Foam Rolling on Skeletal Muscle. Journal of Innovations in Medical Research, 5(2), 9-15.
[20] Yuan, D. (2025). The Impact of Traditional Chinese Non-Pharmacological Therapies on Blood Pressure Control in Community Patients with Hypertension. Current Research in Medical Sciences, 4(5), 8-15.
[21] Yuan, D. (2025). Research on the Intervention of Cancer Patients’ Anxiety by the Concept of “Harmonization of Body and Mind” in Traditional Chinese Medicine. Journal of Innovations in Medical Research, 4(5), 19-25.
[22] Chen, Y. (2026). Standardized Traditional Chinese Medicine External Therapy for Chronic Soft Tissue Pain: A Multicenter Observational Study. Current Research in Medical Sciences, 5(3), 36-45.
[23] Chen, Y. (2026). Construction and Application of Standard System for Traditional External Therapy in Traditional Chinese Medicine Health Preservation. Journal of Innovations in Medical Research, 5(2), 23-31.
[24] Yao, C. (2026). Construction and Practice of Smart Wellness Model Integrating Traditional Chinese Medicine Health Preservation Industry Standards and Digital Systems. Insights in Social Science, 4(2), 76-86.
[25] Mingyang, W. (2026). Why Singapore’ s Healthcare Model Cannot Be Directly Replicated in Mainland China: A Comparative Policy Perspective. Insights in Social Science, 4(2), 24-31.
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Copyright (c) 2026 International Journal of Frontiers of Modern Synthesis