Stroke and dementia rank among the most pressing health issues in Europe. Cerebral small vessel diseases (SVDs) have emerged as a central link between these two major co-morbidities. SVDs account for more than 30% of strokes and at least 40% of dementia cases. They encounter multiple distinct diseases that can be separated based on their underlying genetic defects, risk factors, and clinical presentations. Despite this profound impact on human health, there are no treatments with proven efficacy against SVDs. The applicants have made major progress in identifying key mechanisms involved in SVDs and their co-morbidities. We recently identified blood pressure variability as a major independent risk factor for multiple SVDs, stroke, and dementia and illuminated the roles of the blood brain barrier and the extracellular matrix in small vessel function. We further identified novel molecular pathways (TIMP3, LTBP1, TGFß) that are shared between different SVDs and thus point towards common mechanisms. This EU network, which brings together basic scientists and academic clinicians, will make use of novel animal models and expertly phenotyped patient cohorts to identify key mechanisms common to multiple SVDs and determine how these mechanisms contribute to individual SVDs. We will: i) identify common molecular, cellular, and physiological mechanisms that compromise the function of microvessels in different SVDs; ii) determine how these common mechanistic defects intersect to drive brain damage; and iii) validate the relevance of mechanisms through interventions in experimental systems (isolated microvessels and in vivo) and in patients (exploratory proof of concept trials). Our resources including novel animal models and state-of-the art technologies (e.g. proteomics & ultra-high field MRI) as well as expertise in clinical trials support the feasibility of the approach. In fact, studies by the applicants already revealed novel attractive targets for therapeutic intervention.

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. The key paradigm in the project is the multicentric, synergistic "umbrella" strategy for local data collection, harmonization, and standardization along the entire pre-, in-, and post-hospitalization pathway. By establishing specific common data models (CMDs) implemented in each of the 7 top-tier European clinical centres, 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 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.

Ischemic stroke (IS), caused by occlusion of arteries that supply blood to the brain, remains a leading cause of mortality and morbidity in the world. Disruption of blood and oxygen supply to the brain leads to neuronal death in the ischemic core within minutes. The hypoperfused tissue surrounding the ischemic core, the penumbra, is at high risk for infarction over time but still salvageable. Neuroprotective “bridging”, sustaining the penumbra until reperfusion, may widen the therapeutic window, make recanalization treatments accessible to more patients and improve overall IS outcomes. As ischemic cell death is primarily mediated by hypoxia, increasing oxygen supply to the penumbra seems THE logical approach. In animal models of IS, normobaric hyperoxygenation (NBHO) significantly increased penumbral oxygen pressure and attenuated brain injury when initiated early after onset of ischaemia and vessel occlusion was transient (35 to 50% infarct volume reduction). The PROOF project now seeks to demonstrate that NBHO (high-flow 100% oxygen at >45 L/min via a non-rebreather mask, or FiO2=1.0 for intubation/ventilation) reduces infarct growth from baseline to 24 hours compared to standard treatment if administered ≤3 hours after onset of anterior circulation IS, in patients with proximal vessel occlusion and salvageable tissue at risk. The study is multi-center, adaptive phase-IIb, randomized, open-label with blinded-endpoint (PROBE design). The primary efficacy criterion will be infarct growth from baseline to 24 hours. Secondary endpoints will be NIHSS 24h, categorical shift in the pre-stroke modified Rankin Score, QoL and cognition at day 90. Potential surrogate biomarkers, health economics and societal impacts will be assessed. If NBHO proves its neuroprotective potential in this selected population, phase-III trials in all IS patients may be undertaken. Considering its low costs and ease of use, NBHO may impact stroke care worldwide.

Based on previously developed models and an existing prototype of a clinical decision support system (patent pending), we set out in this project to further develop, test, and validate this clinical decision support for the treatment stratification of acute stroke patients to improve patient outcome. Machine learning (ML)-enabled Artificial intelligence (AI) methods are increasingly adopted in the medical field. Implementing ML-based CDSSs have the potential to be go beyond the current clinical state-of-the-art as AI excels at finding complex and non-linear relationships across a multitude of prognostic variables. AI also has the promise to combine different modalities, such as imaging and clinical values, leading to powerful stratification tools accounting for a multitude of patient sub-populations. Our consortium combines excellence in technical and medical machine learning development with the clinical expertise of three leading stroke hospital partners. Additionally, our consortium benefits from the special expertise in the development of trustworthy AI, software design, and the translation of AI models to the clinical setting with focus on the regulatory process. By leveraging the available medical data and exploiting technological opportunities in the field of AI, and developing and validating trustworthy AI solutions to be implemented in the clinical workflow we are seeking to surpass the clinical state-of-the-art by making a significant and sustainable impact on the treatment of acute stroke that will improve patient survival, outcome and quality of life. The results of our work will serve as a pathway for future projects and we will make our experiences public in the form of standard operating procedures (SOPs) in the areas of development, testing, validation, and regulatory processes.