EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Interoperable clinical data integration for distributed medical AI: The Open Medical Inference Gateway

Pelka, Obioma, Eil, Jan, Manjunatha, Kaushik, Singh, Nimesh, Omeirat, Jazia, Sigle, Stefan und 10 weitere

GMS Medizinische Informatik, Biometrie und Epidemiologie · 22.09.2026 · 22 (Doc11) · Doc11

DOI: 10.3205/mibe000309 ↗

Kurz gefasst

Fachartikel in der Zeitschrift GMS Medizinische Informatik, Biometrie und Epidemiologie, erschienen am 22.09.2026. Verfasst von Pelka und 21 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Integrating AI inference services into clinical workflows remains a persistent challenge, primarily because inference backends and healthcare data standards operate with fundamentally different assumptions. The EU AI Act further requires transparency and traceability for high-risk AI systems in healthcare.

Methods

This paper presents the Open Medical Inference (OMI) Gateway, an interoperability layer that mediates between FHIR- and DICOM-based clinical data environments and heterogeneous AI inference backends. The gateway was implemented in Python using FastAPI with asynchronous job processing via Celery and RabbitMQ. The architecture follows a service-oriented plugin model that separates shared interoperability concerns from service-specific transformation logic. Input and output data are validated against FHIR profiles and DICOM specifications at multiple pipeline stages, producing OperationOutcome resources as a machine-readable audit trail.

Results

End-to-end pipeline latency was measured across 100 sequential inference requests, yielding a median latency of 263 ms and a 100% success rate. The design was evaluated against interoperability requirements from German Medical Informatics Initiative (MII) Data Integration Centers. The system is deployable with a single command and available as open-source software.

Discussion

The results indicate that embedding validation and structured artifact handling directly into the inference execution path yields a more governable and auditable integration model than ad-hoc service adapters.

Schlagwörter

medical informaticsOpen Medical InferencegatewayFHIRDICOMAI inferenceinteroperabilityopen sourceMIIservice-oriented architecture

Zitieren

APA

Pelka, Obioma, Eil, Jan, Manjunatha, Kaushik, Singh, Nimesh, Omeirat, Jazia, Sigle, Stefan, Mathes, Georg, Schweizer, Simon-Tobias, Stump, Shura-Roman, Girdziunaite, …, & Felix (2026). Interoperable clinical data integration for distributed medical AI: The Open Medical Inference Gateway. GMS Medizinische Informatik, Biometrie und Epidemiologie, 22(Doc11), Doc11. https://doi.org/10.3205/mibe000309

Vancouver

Pelka, Obioma, Eil, Jan, Manjunatha, Kaushik, et al. Interoperable clinical data integration for distributed medical AI: The Open Medical Inference Gateway. GMS Medizinische Informatik, Biometrie und Epidemiologie. 2026;22(Doc11):Doc11. doi:10.3205/mibe000309

BibTeX
@article{Pelka2026,
  author = {Pelka and Obioma and Eil and Jan and Manjunatha and Kaushik and Singh and Nimesh and Omeirat and Jazia and Sigle and Stefan and Mathes and Georg and Schweizer and Simon-Tobias and Stump and Shura-Roman and Girdziunaite and Gerda and Nensa and Felix},
  title = {Interoperable clinical data integration for distributed medical AI: The Open Medical Inference Gateway},
  journal = {GMS Medizinische Informatik, Biometrie und Epidemiologie},
  year = {2026},
  volume = {22},
  number = {Doc11},
  pages = {Doc11},
  doi = {10.3205/mibe000309}
}
Kostenlos starten →