Skip to content

FabioLiberti/CIDE

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 

Repository files navigation

Federated Health Data Platforms

Transforming Clinical Silos into Economic Assets. Business Models for European Digital Health Research Networks

Extended Abstract — CIDE 2025

Author: Fabio Liberti University of the Italian Chambers of Commerce (Universitas Mercatorum) & Bambino Gesù Children's Hospital, IRCCS


Overview

This paper proposes a theoretical framework examining how federated learning architectures, integrated with OHDSI's OMOP Common Data Model and HL7-FHIR standards, could enable sustainable business models within the European Health Data Space (EHDS) regulatory context.

Objectives

  1. Infrastructure reuse — Explore how existing OHDSI/FHIR investments can be repurposed for federated architectures, reducing adoption barriers
  2. Business model design — Define theoretical models balancing economic sustainability with EHDS privacy requirements
  3. Trade-off analysis — Analyze the interplay between technical complexity, privacy guarantees, and economic viability

Methodology

Dimension Approach
Technical Hub-and-spoke federated topology leveraging OMOP CDM v5.4 + FHIR R5 APIs, with differential privacy (ε = 0.1–10) and O(n log n) communication complexity
Economic Three conceptual business models: Data Cooperative, Platform-as-a-Service, Innovation Marketplace
Privacy Privacy-utility trade-off analysis mapping EHDS Article 50 requirements to technical capabilities

Key Technical Challenges Addressed

  • Non-IID data distributions across institutions
  • Byzantine fault tolerance for untrusted environments
  • Bandwidth constraints in healthcare networks
  • FHIR-to-OMOP resource mapping (Patient, Observation, Condition)

Preliminary Results

  • Leveraging existing OMOP implementations could reduce integration costs vs. proprietary approaches
  • Minimum viable network: 10–20 institutions for operational sustainability
  • Initial investment: EUR 150–300K per institution (estimated)
  • Moderate privacy settings (ε = 1.0) yield ~5% accuracy degradation while enabling new business models
  • Federated approaches become economically favorable beyond 20 participants

Business Model Comparison

Model Strengths Challenges
Data Cooperative Risk-sharing, collective ownership Governance complexity
Platform-as-a-Service Better scalability Concentrates economic benefits
Innovation Marketplace Highest potential returns Two-sided market bootstrapping

Implications

  • Practitioners: Existing OHDSI/FHIR investments can be leveraged for federated paradigms
  • Policymakers: EHDS regulation can be designed to encourage innovation, not just compliance
  • Researchers: Critical empirical questions identified for future investigation

Future Work

Pilot implementations to validate technical assumptions and economic hypotheses, transforming this conceptual framework into actionable insights for the European health data economy.

Keywords

Federated Learning OMOP Common Data Model HL7-FHIR European Health Data Space (EHDS) Differential Privacy Healthcare Interoperability Digital Health Business Models Clinical Research Networks

Key References

  1. HL7 International, "FHIR R5 Specification," 2025. Available: https://hl7.org/fhir/R5/
  2. OHDSI Collaborative, "The Book of OHDSI," 2021. Available: https://ohdsi.github.io/TheBookOfOhdsi/
  3. OHDSI, "Standardized Data: The OMOP Common Data Model," 2025. Available: https://www.ohdsi.org/data-standardization/
  4. EHDS Regulation, "Regulation on the European Health Data Space (EHDS)," 2025. Available: https://health.ec.europa.eu/ehealth-digital-health-and-care/european-health-data-space-regulation-ehds_it
  5. Haripriya R, Khare N, Pandey M. Privacy-preserving federated learning for collaborative medical data mining in multi-institutional settings. Sci Rep. 2025;15(1):12482. doi: 10.1038/s41598-025-97565-4
  6. Sinaci AA, Gencturk M, Teoman HA, et al. A Data Transformation Methodology to Create Findable, Accessible, Interoperable, and Reusable Health Data. J Med Internet Res. 2023;25:e42822. doi: 10.2196/42822
  7. Soares A, Schilling LM, Richardson J, et al. Making Science Computable Using Evidence-Based Medicine on FHIR. J Med Internet Res. 2024;26:e54265. doi: 10.2196/54265
  8. Katsch F, Hussein R, Stamm T, Duftschmid G. Converting CDA documents to OMOP CDM by leveraging CDA Template definitions. JAMIA Open. 2025;8(2):ooaf022. doi: 10.1093/jamiaopen/ooaf022
  9. Salgado-Baez E, Heidepriem R, Delucchi Danhier R, et al. Toward Interoperable Digital Medication Records on FHIR. JMIR Med Inform. 2025;13:e64099. doi: 10.2196/64099
  10. Li J, Maddock E, Hosking M, et al. Identifying and Optimizing Factors Influencing the Implementation of a FHIR Accelerator. JMIR Med Inform. 2025;13:e66421. doi: 10.2196/66421
  11. Wirth FN, Abu Attieh H, Prasser F. OHDSI-compliance: document templates facilitating the implementation of a software stack for real-world evidence generation. Front Med. 2024;11:1378866. doi: 10.3389/fmed.2024.1378866
  12. Hussein R, Balaur I, Burmann A, et al. Getting ready for the European Health Data Space (EHDS): IDERHA's plan to align with the latest EHDS requirements. Open Res Eur. 2024;4:160. doi: 10.12688/openreseurope.18179.1
  13. Akhmetov A, Latif Z, Tyler B, Yazici A. Enhancing healthcare data privacy and interoperability with federated learning. PeerJ Comput Sci. 2025;11:e2870. doi: 10.7717/peerj-cs.2870
  14. van Drumpt S, Chawla K, Barbereau T, Spagnuelo D, van de Burgwal L. Secondary use under the European Health Data Space: setting the scene and towards a research agenda on privacy-enhancing technologies. Front Digit Health. 2025;7:1602101. doi: 10.3389/fdgth.2025.1602101
  15. Austin JA, Lobo EH, Samadbeik M, et al. Decades in the Making: The Evolution of Digital Health Research Infrastructure Through Synthetic Data, Common Data Models, and Federated Learning. J Med Internet Res. 2024;26:e58637. doi: 10.2196/58637
  16. Gyrard A, Abedian S, Gribbon P, et al. Lessons Learned From European Health Data Projects With Cancer Use Cases: Implementation of Health Standards and IoT Semantic Interoperability. J Med Internet Res. 2025;27:e66273. doi: 10.2196/66273

License

This repository contains materials related to the CIDE 2025 conference submission.

About

Federated Health Data Platforms: Business Models for European Digital Health Research Networks — CIDE 2025

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors