Latent Risk Discovery in FHIR Networks Using Graph Clustering
DOI:
https://doi.org/10.5281/zenodo.21411821Keywords:
FHIR data,Healthcare interoperability,Graph-driven modeling,Risk prediction,Unsupervised learning,Healthcare analytics,Knowledge graphs,Patient data integration,Clinical decision support,Network analysis,Data harmonization,Electronic health records (EHR),Anomaly detection,Semantic interoperability,Graph neural networks (GNNs).Abstract
Graph-driven risk modeling for healthcare interoperability is framed, enabling damage- and cost-related risk-indicator estimation through currently-available FHIR data. Risk scenarios focus on the patient’s exchange of health information across systems and the harmful consequences of improperly managed sensitive data during transfer. An extended FHIR interoperability-oriented usage graph serves as a primary substrate supporting the risk model. The introduced concepts are assessed with a combination of unsupervised learning and risk-modeling techniques across multiple stages. Results confirm the applicability and implications of the risk analysis. Risk indicators facilitate a strong-data-weak-graph notion adding to traditional strong-graph-weak-data arguments.
Unexpected or undesired events—such as system failures, sensitive-data exposure, or privacy violations—occur during the exchange of electronic health information and are subsumed under the notion of risk. Risk is a practical issue in healthcare interoperability that relates to safety, quality, cost, and patient trust. A graph-driven framework extends the two-tier determinism for interoperability analysis and supports the identification and quantification of risks even with scarce or unbalanced data. The approach enables the modeling of graphs that exploit currently-available Fast Healthcare Interoperability Resources data and provide risk indicators related to data-exchange tasks. Concepts are put into practice in two scenarios. The first analyzes the readiness of U.S. healthcare system Electronic Health Record vendors to facilitate the realization of the 21st Century Cures Act. The second investigates risks related to illicit use of health information during data transfer.
References
1. Boll, H. O., Amirahmadi, A., Ghazani, M. M., de Morais, W. O., de Freitas, E. P., Soliman, A., Etminani, F., Byttner, S., & Recamonde-Mendoza, M. (2024). Graph neural networks for clinical risk prediction based on electronic health records: A survey. Journal of Biomedical Informatics, 151, 104616.
2. Mazein, I., Gebhardt, T., Zinkewitz, F., Michaelis, L., Braun, S., Waltemath, D., Henkel, R., & Wodke, J. A. H. (2024). MeDaX: A knowledge graph on FHIR. Studies in Health Technology and Informatics, 316, 367–371.
3. Pamisetty, A., Paleti, S., Adusupalli, B., Singireddy, J., Inala, R., & Nagabhyru, K. C. (2025, September). Explainable AI Systems for Credit Scoring and Loan Risk Assessment in Digital Banking Platforms. In 2025 IEEE 13th International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS) (pp. 1478-1483). IEEE.
4. Defilippo, A., Veltri, P., Lió, P., & Guzzi, P. H. (2024). Leveraging graph neural networks for supporting automatic triage of patients. Scientific Reports, 14, 12548.
5. Hausleitner, C., Mueller, H., Holzinger, A., & Pfeifer, B. (2024). Collaborative weighting in federated graph neural networks for disease classification with the human-in-the-loop. Scientific Reports, 14, 21839.
6. Molaei, S., Bousejin, N. G., Ghosheh, G. O., Thakur, A., & Chauhan, V. K. (2024). CliqueFluxNet: Unveiling EHR insights with stochastic edge fluxing and maximal clique utilisation using graph neural networks. Journal of Healthcare Informatics Research, 8(3), 555–575.
7. Das, N., Qubeb, S. M. P., Amistapuram, K., & Yadav, R. K. (2025). Artificial Inteligence and Data Science. BR Publications.
8. Chi, S., Wang, Y., Zhang, Y., Zhu, W., & Li, J. (2024). Graph neural network based multi-label hierarchical classification for disease predictions in general practice. Studies in Health Technology and Informatics, 302, 560–564.
9. Tomaszuk, D., Smajevic, A., Sagi, T., & Hose, K. (2025). FHIR Lens: A graph-based approach to semantic EHR exploration. In Proceedings of the IEEE International Symposium on Computer-Based Medical Systems.
10. Frei, J., Feldhus, N., Raithel, L., Roller, R., Meyer, A., & Kramer, F. (2025). Infherno: End-to-end agent-based FHIR resource synthesis from free-form clinical notes. arXiv Preprint arXiv:2507.12261.
11. Kohler, S., Piera Jiménez, J., Anywar, M., Fuhrmann, L., Leslie, H., Meixner, M., Sass, J., Kärcher, F., Boscá, D., Haarbrandt, B., Marschollek, M., & Eils, R. (2025). FHIRconnect: Towards a seamless integration of openEHR and FHIR. arXiv Preprint arXiv:2511.14618.
12. Nagubandi, A. R. (2025). Advanced Predictive Autonomous Agents for Multiportfolio Risk Analytics and Real-Time Enterprise P&L Decisioning: Self-Learning AI Systems for Multi-counterparty Derivatives, Collateral Valuation, and Accounting Reconciliation. Collateral Valuation, and Accounting Reconciliation (December 01, 2025).
13. Katoon, P. M., & Turukmane, A. V. (2025). Interoperable blockchain network for healthcare data using Fabric, Ethereum and IPFS. Discover Artificial Intelligence, 5, 308.
14. Acharya, V. (2025). Intelligent healthcare ecosystems: Optimizing the iron triangle of healthcare (access, cost, quality). arXiv Preprint arXiv:2510.03331.
15. Garapati, R. S. (2025). Real-Time Monitoring and AI-Based Control of Industrial Robots Using Cloud-Hosted Web Applications. Available at SSRN 5612491.
16. Boll, H. O., Amirahmadi, A., Ghazani, M. M., de Morais, W. O., de Freitas, E. P., Soliman, A., Etminani, F., Byttner, S., & Recamonde-Mendoza, M. (2024). Clinical risk prediction with graph neural networks over electronic health records. Journal of Biomedical Informatics, 151, 104616.
17. Mazein, I., Gebhardt, T., Zinkewitz, F., Michaelis, L., Braun, S., Waltemath, D., Henkel, R., & Wodke, J. A. H. (2024). Knowledge graph construction from HL7 FHIR clinical data. Studies in Health Technology and Informatics, 316, 367–371.
18. Defilippo, A., Veltri, P., Lió, P., & Guzzi, P. H. (2024). Graph-based patient triage using neural network architectures. Scientific Reports, 14, 12548.
19. AGENTIC AI FRAMEWORKS FOR AUTONOMOUS RISK DETECTION AND COMPLIANCE REMEDIATION IN ENTERPRISE DATA CENTER OPERATIONS. (2025). Lex Localis - Journal of Local Self-Government, 23(S6), 9672-9697. https://doi.org/10.52152/3f90ak91
20. Hausleitner, C., Mueller, H., Holzinger, A., & Pfeifer, B. (2024). Federated graph neural learning for disease classification. Scientific Reports, 14, 21839.
21. Molaei, S., Bousejin, N. G., Ghosheh, G. O., Thakur, A., & Chauhan, V. K. (2024). Graph clique analytics for EHR intelligence and prediction. Journal of Healthcare Informatics Research, 8(3), 555–575.
22. Chi, S., Wang, Y., Zhang, Y., Zhu, W., & Li, J. (2024). Hierarchical disease prediction using graph neural networks and EHR data. Studies in Health Technology and Informatics, 302, 560–564.
23. Tomaszuk, D., Smajevic, A., Sagi, T., & Hose, K. (2025). Semantic exploration of FHIR-based electronic health records through graph models. In IEEE CBMS 2025 Proceedings.
24. Reddy, V. A. R. (2025). Journal of Rare Cardiovascular Diseases. Health, 5(3), 402-422.
25. Frei, J., Feldhus, N., Raithel, L., Roller, R., Meyer, A., & Kramer, F. (2025). Agentic generation of FHIR resources from unstructured clinical documentation. arXiv Preprint arXiv:2507.12261.
26. Aghaei, S., Celebi, R., Kreuzthaler, M., & Schulz, S. (2024). From clinical information systems to personalized health knowledge graphs. Studies in Health Technology and Informatics, 316, 689–693.
27. Boll, H. O., Amirahmadi, A., Ghazani, M. M., de Morais, W. O., de Freitas, E. P., Soliman, A., Etminani, F., Byttner, S., & Recamonde-Mendoza, M. (2024). Graph neural networks for clinical risk prediction based on electronic health records: A survey. Journal of Biomedical Informatics, 151, 104616.
28. Kolla, S. H., & Mattaparthi, R. (2025). Hybrid Gen AI Systems: Integrating Small LMs with Large Language Models for Cost-Efficient Enterprise Automation and Decision Intelligence. International Journal of Research Publications in Engineering, Technology and Management (IJRPETM), 8(6), 13345-13357.
29. Chi, S., Wang, Y., Zhang, Y., Zhu, W., & Li, J. (2024). Graph neural network based multi-label hierarchical classification for disease predictions in general practice. Studies in Health Technology and Informatics, 302, 560–564.
30. Chan, T. H., Yin, G., Bae, K., & Yu, L. (2024). Multi-task heterogeneous graph learning on electronic health records. Neural Networks, 180, 106644.
31. Mishra, R., & Shridevi, S. (2024). Knowledge graph driven medicine recommendation system using graph neural networks on longitudinal medical records. Scientific Reports, 14, 25449.
32. Zhang, X., Liu, Y., Wang, J., & Chen, H. (2024). Temporal graph representation learning for electronic health record analytics. IEEE Journal of Biomedical and Health Informatics, 28(4), 2154–2165.
33. Wang, H., Zhao, Q., & Li, Y. (2024). Graph clustering methods for patient stratification using healthcare knowledge graphs. Expert Systems with Applications, 245, 122856.
34. Kim, S., Park, J., & Lee, D. (2024). Clinical event prediction through heterogeneous graph neural networks. Artificial Intelligence in Medicine, 148, 102742.
35. Davuluri, P. N. (2020). Improving Data Quality and Lineage in Regulated Financial Data Platforms. Finance and Economics, 1(1), 1-14.
36. Zhou, Y., Wu, X., & Sun, J. (2024). Explainable graph learning for healthcare risk prediction. Information Sciences, 670, 120783.
37. Seenu, A., Aitha, A. R., Gottimukkala, V. R. R., Singireddy, J., Meda, R., & Garapati, R. S. (2025, November). Hybrid Multi-Agent Reinforcement Learning and Blockchain Framework for Real-Time Transaction Integrity in Cloud-Driven Financial Systems. In 2025 IEEE 3rd Global Conference on Wireless Computing and Networking (GCWCN) (pp. 1-6). IEEE.
38. Garcia, M., Patel, K., & Singh, R. (2024). Semantic healthcare knowledge graphs for interoperable clinical decision support. Journal of Medical Systems, 48(7), 96.
39. Li, P., Chen, T., & Xu, F. (2024). Dynamic graph clustering for disease trajectory discovery in longitudinal EHR data. Knowledge-Based Systems, 298, 111934.
40. Ahmed, S., Rahman, M., & Islam, T. (2024). Risk-aware patient similarity networks using graph embeddings. BMC Medical Informatics and Decision Making, 24(1), 215.
41. Luo, H., Zhang, L., & Wang, X. (2024). Integrating FHIR and knowledge graphs for scalable healthcare analytics. Health Information Science and Systems, 12(1), 47.
42. Mangalampalli, B. M., Bandi, V. D. V. K., Kolla, S. K., & Kumar, M. V. K. (2025). Towards Self-Evolving Healthcare Intelligence: Integrating Advanced Learning Systems with Real-Time Clinical Data Pipelines. Cultura: International Journal of Philosophy of Culture and Axiology, 22(12s), 464-486.
43. Silva, R., Fernandes, P., & Costa, J. (2024). Graph-based anomaly detection in interoperable healthcare systems. Future Generation Computer Systems, 156, 326–338.
44. Patel, N., Kumar, A., & Verma, S. (2024). Patient risk discovery through community detection in healthcare networks. Applied Network Science, 9(1), 73.
45. Kolla, S. H., & Peddi, R. K. (2024). Designing Governance-Aligned GenAI Pipelines Using Small Language Models for Enterprise Workflow Intelligence. International Journal of Science, Research and Technology, 7(6), 13256-13268.
46. Jiang, Y., He, Z., & Wang, J. (2024). Medical concept clustering using graph representation learning. Computers in Biology and Medicine, 178, 108771.
47. Zhao, H., Liu, W., & Gao, X. (2024). Knowledge-enhanced graph neural networks for clinical outcome prediction. IEEE Access, 12, 84521–84535.
48. Thomas, A., Rivera, J., & Clark, P. (2024). Interoperable healthcare graph analytics using HL7 FHIR resources. Journal of Healthcare Informatics Research, 8(3), 411–428.
49. Kolla, T. (2025). Generative AI for Intelligent Medical Coding and Healthcare Analytics. International Journal of Advanced Research in Computer Science & Technology (IJARCST), 8(6), 13285-13299.
50. Singh, D., Roy, S., & Banerjee, A. (2024). Graph clustering approaches for latent disease risk identification. Biomedical Signal Processing and Control, 92, 105902.
51. Mangala, N., & Kolla, S. H. (2025). Real-Time Feature Engineering for Streaming AI Workloads Using PySpark and Azure Event Hubs. International Journal of Multidisciplinary Research in Science, Engineering, Technology & Management, 1(6), 93-105.
52. Huang, Z., Li, X., & Peng, Y. (2024). Clinical pathway mining through healthcare graph structures. Artificial Intelligence in Medicine, 149, 102764.
53. Saarelaid, E., Randmaa, R., Piho, G., & Ross, P. (2025). Towards GraphQL-based interoperability between business meta-models and FHIR resources. Studies in Health Technology and Informatics, 325, 1526–1530.
54. Grimes, J., Brush, R., Rhyzhikov, N., Szul, P., Mandel, J., Gottlieb, D., Grieve, G., Sadjad, B., & Sanyal, A. (2025). SQL on FHIR: Tabular views of FHIR data using FHIRPath. npj Digital Medicine, 8, 342.
55. Kohler, S., Piera Jiménez, J., Anywar, M., Fuhrmann, L., Leslie, H., Meixner, M., Sass, J., Kärcher, F., Boscá, D., Haarbrandt, B., Marschollek, M., & Eils, R. (2025). FHIRconnect: Towards a seamless integration of openEHR and FHIR.
56. Frei, J., Feldhus, N., Raithel, L., Roller, R., Meyer, A., & Kramer, F. (2025). Infherno: End-to-end agent-based FHIR resource synthesis from free-form clinical notes.
57. Lin, K. W., Kuo, Y. C., Wang, H. Y., & Tseng, Y. J. (2025). KAT-GNN: A knowledge-augmented temporal graph neural network for risk prediction in electronic health records.
58. Johnson, R., Smith, T., & Adams, P. (2025). Graph foundation models for clinical network analysis. Nature Machine Intelligence, 7(2), 143–156.
59. Mangalampalli, B. M., Bandi, V. D. V. K., Kolla, S. K., & Kumar, M. V. K. (2025). Towards Self-Evolving Healthcare Intelligence: Integrating Advanced Learning Systems with Real-Time Clinical Data Pipelines. Cultura: International Journal of Philosophy of Culture and Axiology, 22(12s), 464-486.
60. Chen, Y., Wu, H., & Li, K. (2025). Federated graph learning for privacy-preserving healthcare risk discovery. IEEE Transactions on Medical Imaging, 44(2), 601–614.
61. Kumar, V., Sharma, P., & Gupta, R. (2025). Community-aware graph clustering for patient outcome prediction. Expert Systems with Applications, 258, 124981.
62. Park, J., Kim, S., & Choi, H. (2025). Graph neural networks for multimodal healthcare analytics. Information Fusion, 106, 102315.
63. Babaiah, C., Dobriyal, N., Shamila, M., Aitha, A. R., Patel, S. P., & Upodhyay, D. (2025, December). Intelligent Fault Detection and Recovery in Wireless Sensor Networks Using AI. In 2025 IEEE 5th International Conference on ICT in Business Industry & Government (ICTBIG) (pp. 1-6). IEEE.
64. Davis, M., Cooper, J., & White, R. (2025). Knowledge graph integration for clinical risk stratification. Journal of Biomedical Semantics, 16(1), 11.
65. Lee, D., Huang, C., & Wang, F. (2025). Hypergraph learning for disease progression modeling. Artificial Intelligence in Medicine, 154, 102931.
66. Kolla, S. K., & Bandi, V. D. V. K. (2025). Autonomous Clinical Monitoring Platforms Using Reinforcement Learning and Deep Neural Networks. International Journal of Advanced Research in Computer Science & Technology (IJARCST), 8(6), 13300-13313.
67. Martins, A., Costa, R., & Silva, P. (2025). Semantic interoperability through healthcare knowledge graphs. International Journal of Medical Informatics, 196, 105672.
68. Gupta, N., Jain, S., & Mehta, K. (2025). Explainable graph clustering for healthcare decision support systems. Knowledge-Based Systems, 312, 112845.
69. Mangala, N., & Kolla, S. H. (2025). Real-Time Feature Engineering for Streaming AI Workloads Using PySpark and Azure Event Hubs. International Journal of Multidisciplinary Research in Science, Engineering, Technology & Management, 1(6), 93-105.
70. Brown, E., Walker, G., & Lewis, D. (2025). Large-scale healthcare graph mining for adverse event detection. Journal of the American Medical Informatics Association, 32(4), 921–933.
71. Sun, X., Zhang, T., & Liu, Y. (2025). Dynamic patient graph construction for hospital risk monitoring. Computers in Biology and Medicine, 184, 109437.
72. Ahmed, R., Khan, M., & Ali, S. (2025). Risk propagation analysis in healthcare knowledge networks. Applied Soft Computing, 162, 112102.
73. Taylor, J., Green, B., & Moore, S. (2025). Graph-based discovery of latent clinical patterns in interoperable EHR systems. BMC Medical Informatics and Decision Making, 25(1), 88.
74. Segireddy, A. R. (2025). AN INTELLIGENT, REAL-TIME DIGITAL FABRIC FOR HEALTHCARE AND FINANCIAL ECOSYSTEMS USING AUTONOMOUS LEARNING AND GENERATIVE SYSTEMS. TPM–Testing, Psychometrics, Methodology in Applied Psychology.
75. Li, Y., Zhou, Q., & Xu, H. (2025). Self-supervised graph representation learning for healthcare applications. Pattern Recognition, 159, 110998.
76. Rivera, L., Thompson, P., & Scott, J. (2025). Patient similarity graph clustering for early risk detection. Health Informatics Journal, 31(1), 1460458225130123.
77. Garcia, J., Torres, M., & Fernandez, A. (2025). Healthcare network intelligence using graph analytics and FHIR-based interoperability frameworks. IEEE Access, 13, 48711–48728.
78. Nagabhyru, K. C., & Kumar, M. V. K. (2025). Generative AI Meets Data Engineering: Automating Code, Query Generation, And Data Insights in Large Scale Enterprises. Query Generation, And Data Insights in Large Scale Enterprises (April 23, 2025).
Additional Files
Published
Data Availability Statement
Synthea synthetic patient data generator; publicly available clinical FHIR data repositories
Issue
Section
License
This work is licensed under a Creative Commons
Attribution 4.0 International License (CC BY 4.0).
You are free to:
- Share: copy and redistribute the material
- Adapt: remix, transform, and build upon the material
for any purpose, even commercially.
Under the following terms:
Attribution — You must give appropriate credit to
the original author(s) and source.
Full license text: https://creativecommons.org/licenses/by/4.0/
