Skip to main content

Programme Category


Article available in the folowing languages:

Access and integration of heterogeneous health data for improved healthcare in disease areas of high unmet public health need

Over the past few years, there has been an explosion in the generation of data that could be harnessed for use in healthcare delivery and research. These data include data generated by digital technologies and patient reported outcome and experience measures, as well as data from clinical trials and routine clinical care. However, accessing, integrating & analysing these data to maximise the value for patient care and research is extremely challenging.

This topic aims to provide a scalable platform for the seamless integration or linkage of these diverse data at scale, and develop tools to allow the data to be used in clinical care, patient self-management and research in disease areas of high unmet public health.

For their proposed activities applicants should clearly identify a disease area of high unmet public health need1 taking into account comorbidities and/or functional status, and explain their choice with empirical evidence where possible.

  • Develop / further develop a scalable, open platform for the seamless integration or linkage of data at scale from diverse public and private data sources relevant to the disease area selected. These data sources should, as a minimum, include all of the following: clinical trials; registries; patient safety data; routine clinical care; publicly available health insurance data; patient reported outcome and experience measures; and data generated by digital technologies such as sensors, wearables and mHealth apps. Preferably, projects should also integrate data that has not usually been used before for the purpose of medical decision-making.
  • Develop / further develop tools focused on the needs of patients, leveraging these diverse data sources to support patient self-management and empower joint healthcare professional - patient decision making.
  • Develop / further develop clinical (and other) decision support systems leveraging these diverse data sources to allow clinicians to deliver better healthcare services to patients in the disease area selected.
  • Demonstrate the added value of the platform and tools compared to current approaches through a use case (study) applied to the disease area selected.
  • Demonstrate the widespread applicability and scalability of the platform & tools using data sources from outside of the project
  • Publish sufficient information, including access protocols, on the data that has been used in the project to facilitate long-term access and re-use, while ensuring compliance with the General Data Protection Regulation and other relevant European legislation.

Applicants should also aim to deliver the following:

  • Public release of a set of minimum technical requirements for the developed platform/tools that includes interoperability, connectivity, data protection, cybersecurity and authentication/identification requirements that need to be met to allow the efficient integration of additional data from new devices/sensors/sources into the decision-support system after the project ends.
  • Sustainable, ideally open-source tools that help ensure the quality and FAIRness[[]] of data at source (e.g. automated tools to help data entry, semantic coding, and data management in particular in registries and databases maintained by healthcare professionals/providers and research institutions) as well as methodologies, quality standards and metrics to assess data quality.
  • Sustainable tools to increase cross-border and cross-sector interoperability of health data from the diverse sources mentioned above. Ideally, these tools use open exchange formats and take into account relevant EU initiatives including the eHealth Digital Services Infrastructure (eHDSI)2 and the European Electronic Health Record Exchange Format (EEHRxF)3
  • Sustainability plan/business model to ensure the long-term impact of the project results.

Other considerations:

  • Applicants should build on clearly identified existing tools & platforms where possible, and ensure that the platform and tools developed can be applied to other disease areas or be relevant for other scientific and clinical communities (i.e. ensuring interoperability with other solutions). If applicants choose to develop a new data platform, a strong justification must be provided.
  • Applicants must demonstrate that they have access to sufficient diverse data, including from industry sources, to meet the objectives of this topic. The data sources (name & country), types, and size must be described in the proposal alongside convincing evidence that the consortium will have access to these data for the project implementation.
  • During their activities, applicants should ensure appropriate engagement of the end-users of the developed tools, especially patients and healthcare professionals.
  • Applicants are expected to explore the integration of the outputs with the European Health Data Space (EHDS)4 when it becomes operational, and explore synergies with other relevant health data initiatives and projects.

1 Unmet public health needs are needs currently not addressed by healthcare systems for various reasons, for example if no medicines are known to treat a disease. Areas of public health importance are those where the burden of disease is high for patients and society due to the severity of the disease (in terms of mortality, physical and functional impairment, comorbidities, loss of quality of life…) and/or the number of people affected by it. For example, Alzheimer’s disease.




This topic aims to achieve the following:

  • Better and faster integration of future products, services and tools along the healthcare pathway, responding to patients’ specific needs and leading to improved health outcomes, patient safety and patient well-being.
  • Wider availability of interoperable, large scale, quality data, respecting FAIR principles1 facilitating research and the development of integrated products and services.
  • Advanced analytics/artificial intelligence (AI) supporting health research & innovation, resulting in:a) clinical decision support for increased accuracy of diagnosis and efficacy of treatment;b) wider availability of personalised health interventions to end-users;c) better evidence of the added value of new digital health and AI tools, including reduced risk of bias due to improved methodologies.

1 Wilkinson, M., Dumontier, M., Aalbersberg, I. et al. The FAIR Guiding Principles for scientific data management and stewardship. Sci Data 3, 160018 (2016).