AIQNET - Medical Data Ecosystem
AIQNET Project Archive and Case Study
Project Snapshot
AIQNET is a federally funded digital healthcare project focused on building an interoperable, AI-enabled medical data ecosystem. The project addressed a central challenge in healthcare digitization: medical and clinical data exists in large volumes, but is fragmented across systems, poorly standardized, and difficult to use in a legally compliant way.
The consortium was led by RAYLYTIC GmbH, which coordinated partners from healthcare providers, medical device manufacturers, software companies, and research institutions.
Project period: 2020–2022
Funding: German Federal Ministry for Economic Affairs and Climate Action
Consortium: 16 funded partners plus associated partners
Consortium lead: RAYLYTIC GmbH (Leipzig)
Background and Motivation
Hospitals, medical devices, and healthcare software systems generate vast amounts of data every day. In practice, this data is often locked into isolated systems, stored in incompatible formats, or requires extensive manual effort to reuse. At the same time, regulatory requirements, data protection rules, and ethical considerations significantly limit how medical data can be shared.
AIQNET was initiated to address these issues holistically. Instead of building another standalone platform, the project set out to create an ecosystem that enables secure data exchange, standardization, and AI-based analysis across organizational and technical boundaries.
The project originated from the federal AI innovation competition in 2019, where the consortium’s proposal was selected for large-scale funding.
RAYLYTIC as Consortium Leader
As consortium leader, RAYLYTIC was responsible for the strategic direction and operational coordination of AIQNET. This included aligning technical development, regulatory considerations, and partner interests across a large and diverse consortium.
Key responsibilities included:
overall project coordination and governance
definition of the ecosystem architecture and data strategy
integration of AI-based analytics into clinical and regulatory workflows
alignment of technical solutions with legal and ethical requirements
RAYLYTIC’s experience in clinical data analysis and real-world evidence played a central role in shaping the project’s analytical and methodological foundation.
Technical Approach
AIQNET was designed as a modular ecosystem rather than a centralized data platform. The focus was on interoperability, reusability, and data sovereignty.
Interoperability and Standards
The project relied on established healthcare standards such as FHIR and SMART on FHIR to connect heterogeneous systems. This made it possible to exchange data between hospital IT systems, medical devices, and software tools without requiring fundamental changes to existing infrastructure.
Data Governance and Security
Data ownership remained with the respective data holders. Patient-related data was processed using anonymization and pseudonymization concepts, supported by consent and access management mechanisms. This ensured compliance with GDPR and other regulatory requirements.
Structured and Unstructured Data
AIQNET addressed both structured datasets and unstructured sources such as clinical reports or device logs. AI-based methods were applied to transform these sources into structured, analyzable data.
Use Cases and Practical Validation
The ecosystem was validated through concrete use cases contributed by consortium partners. These use cases covered clinical, technical, and regulatory scenarios, including:
integration of medical device data into hospital IT environments
support for post-market clinical follow-up and regulatory documentation
standardized access to clinical and device data for analytics and research
These applications ensured that the project delivered practical value rather than remaining at a conceptual level.
Outcomes and Results
AIQNET produced a set of concrete outcomes that extended beyond pilot demonstrations.
Operational Interoperability
The project demonstrated that heterogeneous healthcare systems can be connected in practice using shared standards. Hospitals, manufacturers, and software providers successfully exchanged data without replacing their existing systems.
Reusable Data Infrastructure
Instead of a closed solution, AIQNET delivered reusable components for data ingestion, harmonization, and access. These components can be applied to new partners and use cases, reducing integration effort in follow-up projects.
AI-Ready Clinical and Device Data
Fragmented clinical and medical device data was transformed into structured, analyzable datasets. This enabled downstream analytics, reporting, and evidence generation without extensive manual preprocessing.
Support for Regulatory and Clinical Evidence
Several use cases focused on post-market clinical follow-up and real-world evidence. AIQNET showed that interoperable data pipelines can significantly reduce the effort required to collect, structure, and analyze regulatory-relevant data.
Legally Compliant Data Governance
The project implemented applied governance frameworks covering consent management, pseudonymization, and controlled data access. These were tested in real partner scenarios and demonstrated that legal compliance and data-driven innovation are compatible.
Cross-Sector Collaboration
AIQNET established a functioning collaboration model between healthcare providers, medtech companies, and software vendors. This reduced organizational friction and clarified responsibilities for data access and usage.
Ecosystem Growth
Beyond the funded consortium, additional associated partners joined the ecosystem. This indicated that the approach was viable and attractive beyond a closed research context.
Impact and Legacy
AIQNET established a reference model for interoperable, AI-enabled medical data ecosystems. The project showed that healthcare data silos can be connected without centralizing sensitive data and that interoperability standards can be applied in operational settings.
For RAYLYTIC, AIQNET reinforced its role as a strategic partner for data-driven healthcare innovation, with proven expertise at the intersection of AI, interoperability, and regulatory requirements. The project outcomes continue to inform follow-up initiatives and real-world applications in digital health and medical technology.