The COVID-X team is delighted to announce the final release of its data-driven Sandbox, one of the most important milestones of the project.
Significant clinical information permits clinicians and clinical staff to create educated choices to make strides in the quality of care. All European healthcare frameworks collect and store clinical information, but shockingly, most of this healthcare information is sitting around in data silos, in unstructured formats and usually not easily accessible to interested communities. Hence, homogeneous and harmonized data is primarily unused within the arrangement of care but regularly holds essential information and insights that contribute to cultivating superior care of all patients.
The COVID-X programme bridges the gap between tech companies and healthcare providers by boosting data-driven solutions with the power to overcome clinical challenges in the fight against the COVID-19 pandemic. COVID-X selects and offers direct funding to competitive and market-oriented European SMEs and Start-Ups, the COVID-X Game Changers, accessing ethical, technical and business mentoring to validate their solutions with real life, accessible, harmonized and appropriately annotated retrospective quality clinical data, the hardest to get access to.
COVID-X envisions the provision of the COVID-X Sandbox and its Data-driven services, as the enabling core data-driven platform for aggregating, curating, structuring, cataloguing and providing seamless interoperable access to anonymized health data from retrospective data sets of Clinical partners, and, when needed, to data from open data sources, as well as to streaming data from connected medical devices/apps.
These services are augmented by security, information visualization and data analytics/federated validation services. The purpose of the COVID-X Sandbox is to provide core services both to Clinical partners/data providers to ingest data into the Sandbox, and to Solution Providers to integrate their solution with the Sandbox and consume and manage data.
The external technology providers, thus, selected to be funded in the COVID-X Programme, integrate their solutions with the COVID-X Sandbox, which on the one hand provides core data-driven services, as listed above and in Figure 1 (data ingestion, harmonization, unified description and annotation, (meta)data storage and cataloguing, security, data query, search and retrieval, unified and interoperable data access, data visualization and federated learning services), while on the other hand, provides CI/CD tools and infrastructure to support automated CI/CD pipelines for software integration, testing, containerization and deployment of Game Changers solutions when integrating them with the Sandbox. Single solution providers validate their solution at one of the three COVID-X project pilot sites in Italy, Spain, and Sweden. Each site is focused on specific clinical challenges and target data. The team solution providers, involving their own clinical partner, pilot their solutions with the integration of their clinical data, managed and interoperably provided by the COVID-X Sandbox.
We are delighted to announce that we have selected 16 solutions during the 1st COVID-X open call and 13 solutions during the 2nd open call. These projects benefit (and have acknowledged as much) in multiple ways from the COVID-X Sandbox, its data-driven services, its catalogue of relevant data (accompanied with their terms of access) and its CI/CD capabilities.
The 1st release of the COVID-X Sandbox, launched in April 2021, included core prioritized data-driven services comprising of data integration services of retrospective health data sets, as well as streaming data and open data sets, real-time data ingestion services, data annotation, indexing, cataloguing and storage services, security services, data access/filtering/search/querying and data visualization services, encompassing, in addition, an API Gateway to seamlessly provide access to these services to Third-party solution providers.
We are proud to announce that the final release of the COVID-X Sandbox has now been launched. Figure 1 presents an overview of the complete set of data-driven services that comprise its architecture, including data integration, data harmonization, filtering and cataloguing, data storage, query and retrieval, security in data access, data visualization. In the final release, on the one hand, unified data modeling, annotation and access is further enhanced for data interoperability purposes, while the federated learning service is offered to permit the deployment of federated learning edge nodes in the targeted hospitals enabling remote and secure retraining of AI algorithms over diverse types of data (numerical, textual, time-series, images such as scans, etc.) across many data providers of similar data sets. Clinical partners provide the same types of health data while maintaining the integrity and security of data and meeting the hospitals’ needs. The objective is to properly handle personal health data and increase data providers’ trust, as federation is performed at Data providers’ sites, instead of moving sensitive data to third party infrastructures.
By the end of July 2021, the end date of Sprint 1 of COVID-X Acceleration Programme for OC#1 Game Changers, Single and Team solutions have been successfully integrated data- and/or software-wise. Data from external Clinical partners of Team Solutions have been successfully integrated into the COVID-X Sandbox, providing a uniformly annotated distributed COVID-19 health data catalogue and space (with data access policies enforcement where necessary).
The COVID-X Sandbox has been deployed for OC1 Game Changers and will be installed for OC2 ones both at a cloud computing infrastructure, accessible by all, or the provided infrastructure of Clinical partners according to needs.
In the final release, additional open and publicly available datasets will be ingested in the Sandbox, originating from the Clinical Partners of the OC2 Game Changers.
FIGURE 1 – Final COVID-X Sandbox Release providing a complete set of core data-driven services