Technology Platform

Within HiGHmed, we will join forces to create three Medical Data Integration Centers (MeDICs) based on a generic and scalable reference architecture for integrating data from care, research, and external sources, which will facilitate the development of new solutions for medical data analytics benefitting clinicians, patients and researchers. Uniquely, this consortium integrates novel and emerging data types such as genomics and radiomics through the research-oriented partner, the DKFZ, where a complementary omics data integration center will be established.

The long-term vision for HiGHmed is to develop a joint technology platform across all university hospitals and research units that will swiftly assist and promote data-based knowledge-building and decision-making processes in patient-centric diagnostics, treatment and care. The concept will be developed in line with three prototypical use cases and rolled out to further clinical partners in medium to long-term. HiGHmed will develop a joint cross-institutional reference architecture based on relevant existing standards such as IHE, openEHR and FHIR. This includes profiling these standards and agreeing on common semantics for real-life implementation. The reference architecture will be scalable and open for adoption by additional partner hospitals, as well as for many solution developers to provide innovative applications, e.g. for data integration or analytics.

The design of the HiGHmed technology platform was guided by the following ten core principles:

  1. Patients first: In addition to fine-grained use and access control, patients will be able to view and obtain their health data through user friendly tools.
  2. Data Safety and Privacy: Data safety and privacy and the patients’ right of self-determination are highest priorities. Data access is regulated unambiguously in a transparent and traceable process.
  3. Clinical Relevance: Clinical relevance, not mere technical feasibility, has been the driver for our medical use cases and design decisions.
  4. Clinically led Data Modelling: Healthcare professionals and researchers alike need to be actively engaged to establish semantic interoperability. This creates a new clinico-technical role, the so-called Data Steward, responsible for the management and fitness of data elements within the MeDICs.
  5. Semantic Traceability: Semantic models need to be computable. Data steward-supported, single source modelling is a mandatory precondition in a distributed environment to enforce semantic traceability from healthcare to research through all software layers at all sites.
  6. Proven Technology: Robust and practice-approved technology supported by industry and well established open source projects are preferred over research prototypes and proof-of-concepts.
  7. Scalability: Technical solutions must be optimized to handle high volumes of complex, constantly changing information and clinical workflows. However, a good balance between technical standardization and flexibility regarding the organization and configuration of each particular MeDIC is needed. An interoperable interface for any MeDIC outside of HiGHmed is thus ensured.
  8. Sustainability: The underlying platform technology will be affected by progress in information technologies. We seek to externalize knowledge artefacts as clinical content models, terminologies, guidelines, algorithms, queries etc. by expressing them in technology neutral and open formats, allowing the data and their definitions to efficiently migrate from one technology stack to another.
  9. Decentralization: Patient data will reside at each particular site. Until access is needed by a network participant and patient consent has been given, no data will be transferred between partners data repositories.
  10. Enable Innovation: Finally, HiGHmed as an organization stands for innovation. Therefore, we only consider technologies as appropriate that allow us to create innovative applications, mobile apps and analytics.

Our technology concept builds on three medical use cases, which will support requirement analysis and validation.