Periodic Reporting for period 1 - IDEA4RC (Intelligent Ecosystem to improve the governance, the sharing and the re-use of health Data for Rare Cancers)
Reporting period: 2022-09-01 to 2024-02-29
Rare cancers comprise more than 200 different tumours, 74% of which have an annual incidence rate below one case every 200,000 European citizens.
Taken together rare cancers account for about 20%-25% of all new cancer diagnoses, nonetheless knowledge on rare cancers is scarce due to small sample sizes and lack of data. Clinical and translational research need large international collaborations exploiting networks specialized in rare cancers, that pool knowledge and data together.
The IDEA4RC ambition is to establish the framework for a first-in-the-field European data ecosystem for rare cancer linking in a federated network data provided by eleven centres of the European Reference Network on rare adult solid cancers (EURACAN), including about 70 health care providers in 26 EU Member States.
The IDEA4RC ecosystem builds on a federation of local data repositories, the IDEA4RC capsules, hosted at each EURACAN centre and totally interoperable. Access to the capsules will be governed by data access permits, rules and conditions tailored to the specific needs and constraints of each centre. Thus, not only data will never leave the centre, but data analysis and processing will be performed on each local capsule and only aggregated data will be shared. AI tools will be built to enable multi-language data processing and analysis; a data navigator will assist clinicians and researchers in finding and accessing available data of stipulated quality and modern trust-building technologies will orchestrate data governance. The developed tools will be tested in relevant pilot cases across 11 EURACAN centres .
The rare cancer data ecosystem realized in the project will advance clinical research contributing to improve the quality of care, patients’ access to optimal diagnosis and treatment, so that ultimately all patients have equal access to high quality specialist care all over EU, in compliance with principle 16 of the European Pillar of Social Rights.
Pathways to scale towards significant impact revolve around: (i) coordination with EURACAN governing bodies to propose the data ecosystem to other centres; (ii) dissemination towards other ERNs on rare diseases; (iii) creation of a community of interest among wider audience of interested stakeholders; (iv) possible commercial exploitation of software technologies developed within the project.
Taken together rare cancers account for about 20%-25% of all new cancer diagnoses, nonetheless knowledge on rare cancers is scarce due to small sample sizes and lack of data. Clinical and translational research need large international collaborations exploiting networks specialized in rare cancers, that pool knowledge and data together.
The IDEA4RC ambition is to establish the framework for a first-in-the-field European data ecosystem for rare cancer linking in a federated network data provided by eleven centres of the European Reference Network on rare adult solid cancers (EURACAN), including about 70 health care providers in 26 EU Member States.
The IDEA4RC ecosystem builds on a federation of local data repositories, the IDEA4RC capsules, hosted at each EURACAN centre and totally interoperable. Access to the capsules will be governed by data access permits, rules and conditions tailored to the specific needs and constraints of each centre. Thus, not only data will never leave the centre, but data analysis and processing will be performed on each local capsule and only aggregated data will be shared. AI tools will be built to enable multi-language data processing and analysis; a data navigator will assist clinicians and researchers in finding and accessing available data of stipulated quality and modern trust-building technologies will orchestrate data governance. The developed tools will be tested in relevant pilot cases across 11 EURACAN centres .
The rare cancer data ecosystem realized in the project will advance clinical research contributing to improve the quality of care, patients’ access to optimal diagnosis and treatment, so that ultimately all patients have equal access to high quality specialist care all over EU, in compliance with principle 16 of the European Pillar of Social Rights.
Pathways to scale towards significant impact revolve around: (i) coordination with EURACAN governing bodies to propose the data ecosystem to other centres; (ii) dissemination towards other ERNs on rare diseases; (iii) creation of a community of interest among wider audience of interested stakeholders; (iv) possible commercial exploitation of software technologies developed within the project.
The following results have been achieved in the reporting period:
1. the design of the ecosystem involving all stakeholders in co-creation activities
2. the user’s needs that will inform the design of the ecosystem architecture
3. the IT solutions for data standardization and common data models application, and the data models for sarcomas and head and neck cancers
4. following the definition of data models, data standardization was defined:
a. the FHIR implementation guide
b. the inclusion of OMOP common data model and the interoperability with FHIR, to facilitate the integration of data from all EURACAN hospitals
c. the metadata taxonomy
5. the tools for unstructured data annotation and for the integration of unstructured data from multilingual sources
6. the pilot use cases that will be used to test the system in real environments
7. the data governance framework, workflow and requirements
8. the pilot technical deployment started in pilot sites
9. the engagement of stakeholders for a wider community of interest involving patients' advocacy and all kinds of users
10. dissemination web site, newsletters, communications via media, press and social media and a Dissemination and communication plan
11. an attentive ethics monitoring conducted by independent ethics advisors external to the Consortium
12. pilot implementation of FHIR capsules in three EURACAN centres
1. the design of the ecosystem involving all stakeholders in co-creation activities
2. the user’s needs that will inform the design of the ecosystem architecture
3. the IT solutions for data standardization and common data models application, and the data models for sarcomas and head and neck cancers
4. following the definition of data models, data standardization was defined:
a. the FHIR implementation guide
b. the inclusion of OMOP common data model and the interoperability with FHIR, to facilitate the integration of data from all EURACAN hospitals
c. the metadata taxonomy
5. the tools for unstructured data annotation and for the integration of unstructured data from multilingual sources
6. the pilot use cases that will be used to test the system in real environments
7. the data governance framework, workflow and requirements
8. the pilot technical deployment started in pilot sites
9. the engagement of stakeholders for a wider community of interest involving patients' advocacy and all kinds of users
10. dissemination web site, newsletters, communications via media, press and social media and a Dissemination and communication plan
11. an attentive ethics monitoring conducted by independent ethics advisors external to the Consortium
12. pilot implementation of FHIR capsules in three EURACAN centres
IDEA4RC encompasses cutting-edge methodologies, technologies, and strategies aimed at advancing healthcare data management, research, and innovation, with a focus on addressing the challenges posed by research on rare cancers and, particularly, privacy preserving data processing. IDEA4RC's innovative solutions not only drive advancements in oncology research but also intend to adhere to the approach being established by the EHDS regulation.
IDEA4RC's data model is being designed following the newer and most adopted standard terminologies to facilitate collaboration and data sharing among healthcare stakeholders across Europe.
The project also emphasizes the identification, protection, management, and exploitation of valuable intellectual property arising from its outcomes. It employs mechanisms such as open-source licensing, patents, copyrights, and trade secrets to safeguard innovations and maximize their impact.
By aligning with industry standards like OMOP and FHIR, IDEA4RC facilitates the exchange of healthcare data in a format that makes it easier to comply with the EHDS regulation.
IDEA4RC zero-trust philosophy and service mesh technology ensure a secure processing environment for privacy-preserving data processing. IDEA4RC robust security measures and encryption protocols, safeguard sensitive healthcare data from unauthorized access or breaches, in alignment with EHDS principles for the protection of patient privacy and confidentiality in all data processing activities.
IDEA4RC innovative data governance approach based on social sciences and humanities research reflects EHDS goals of promoting responsible research and innovation. IDEA4RC transparent policies and procedures for data collection, storage, and usage ensure compliance with regulations regarding data governance. The integration of technologies like blockchain enhances data traceability and integrity, further aligning with EHDS objectives of fostering trust and accountability in healthcare data management.
Finally, IDEA4RC will develop Natural Language Processing algorithms to tackle the scarcity of structured health data most of which is currently available in natural language text. By transforming such texts into structured variables, conducive to automated analysis, IDEA4RC NLP algorithms will enhance the usability and interoperability of healthcare data for secondary use, including scientific research, aligning with one of the main EHDS objectives.
IDEA4RC's data model is being designed following the newer and most adopted standard terminologies to facilitate collaboration and data sharing among healthcare stakeholders across Europe.
The project also emphasizes the identification, protection, management, and exploitation of valuable intellectual property arising from its outcomes. It employs mechanisms such as open-source licensing, patents, copyrights, and trade secrets to safeguard innovations and maximize their impact.
By aligning with industry standards like OMOP and FHIR, IDEA4RC facilitates the exchange of healthcare data in a format that makes it easier to comply with the EHDS regulation.
IDEA4RC zero-trust philosophy and service mesh technology ensure a secure processing environment for privacy-preserving data processing. IDEA4RC robust security measures and encryption protocols, safeguard sensitive healthcare data from unauthorized access or breaches, in alignment with EHDS principles for the protection of patient privacy and confidentiality in all data processing activities.
IDEA4RC innovative data governance approach based on social sciences and humanities research reflects EHDS goals of promoting responsible research and innovation. IDEA4RC transparent policies and procedures for data collection, storage, and usage ensure compliance with regulations regarding data governance. The integration of technologies like blockchain enhances data traceability and integrity, further aligning with EHDS objectives of fostering trust and accountability in healthcare data management.
Finally, IDEA4RC will develop Natural Language Processing algorithms to tackle the scarcity of structured health data most of which is currently available in natural language text. By transforming such texts into structured variables, conducive to automated analysis, IDEA4RC NLP algorithms will enhance the usability and interoperability of healthcare data for secondary use, including scientific research, aligning with one of the main EHDS objectives.