UMBRELLA is a holistic approach to progress, reshape, and benchmark the overall stroke care pathway and set new and improved standards of care in terms of primary and secondary prevention, rapid access to treatments, early accurate diagnosis, stratification, management and real-time monitoring, therapeutic targets identification, and rehabilitation, recurrent stroke and related cardiovascular events. This innovative approach will transform healthcare systems by improving and harmonizing professionals' workflows in a more patient-centred, digitalized, and communicative manner. UMBRELLA aims to revolutionize stroke management by implementing a comprehensive approach that addresses gaps along the whole continuum of the stroke care pathway.
UMBRELLA will create a federated data platform (U-platform) where Real World Data (RWD)-based AI algorithms can be locally created and validated, to advance personalised diagnosis, risk prediction, and treatment decisions in the acute and post-acute phases of stroke. The algorithms will be then trained in a decentralized manner through a federated learning infrastructure (FL-platform), which preserve data security and privacy, avoiding data centralization or exchange across centres but fostering collective AI-models training. On the other hand, standardized stroke management protocols and procedures will be created and/or implemented across the participating centres, including the validated usage of advanced digital technologies as solutions to facilitate data collection, visualization, patient engagement, monitoring, outcomes integration, and decision-making across the whole stroke pathway.
Six specific objectives (OBs) have been defined to achieve the project's main goal. Specific Measures of Success (MoS) and Key Performance Indicators (KPIs) have been identified for each objective, which will be used to monitor and evaluate progress throughout the project duration.
OB1. To integrate, harmonize and standardize in a federated manner local retrospective and prospective data collection, as well as stroke protocols and procedures across the whole stroke care pathway.
OB2. To build and enhance a multi-country federated Real World Data (RWD) platform (U-platform) that allows the local creation and validation of trustworthy AI models to advance personalized stroke diagnosis, risk prediction, and decision-making.
OB3. To implement and exploit a Federated Learning framework (FL-platform) that allows the training of the U-platform-AI models across various centres while preserving data security and privacy.
OB4. To improve stroke patients’ outcomes and interoperable silos' communication with novel digital technologies for patients' engagement, real-time monitoring, data visualization, and decision-making.
OB5. To develop a roadmap to regulatory compliance and future certification for the selected improved stroke cases' management and the UMBRELLA FL-platform.
OB6. To develop a roadmap for the long-term sustainability and exploitation of UMBRELLA advancements in stroke care and a plan for dissemination.