Imagine a smart medical system that learns from many hospitals without ever actually seeing or stealing private patient files. It acts like a collective brain that helps doctors predict if a stroke patient will recover their independence or if they are likely to have another stroke. It also gives patients a simple app to understand their own health journey better.
Stroke causes severe global disability and high economic burdens, with a 25% recurrence risk. Clinicians lack trustworthy, privacy-compliant tools to predict recovery and prevent readmissions.
A Federated Learning platform and a patient empowerment app that predict stroke outcomes and recurrence risks using clinical and remote-monitored data.
If you are a software developer dealing with strict data privacy laws—this project developed a Federated Learning platform that allows AI training across multiple sites without moving sensitive data. This enables the creation of validated predictive models for stroke risk assessment while remaining compliant with security protocols.
If you are a hospital network dealing with high readmission rates—this project developed AI tools to predict clinical worsening and unplanned hospital readmissions. This allows for personalized stroke management to prevent early clinical worsening.
If you are a remote monitoring company dealing with fragmented patient data—this project developed a system integrating outpatient monitored data from home-care systems. This allows for a more accurate assessment of cardiovascular risk factors and treatment compliance.
Based on available project data, no specific pricing or cost information is provided as this is a research-funded project.
Yes, the project specifically aims to create a flexible and scalable platform designed for scaling-up with new hospitals and new pathologies.
Based on available project data, the specific IP and licensing terms are not disclosed, though it involves a consortium of 13 partners.
The platform uses Federated Learning (FL) to leverage data without compromising privacy, implementing best-in-class security and privacy protocols.
The project includes a proof of concept study in relevant application environments and User Experience studies to ensure usability for healthcare professionals.
The consortium is heavily weighted toward research and clinical expertise, with 7 research organizations and 3 universities. However, there is a 15% industry participation rate consisting of 2 industry partners, including 1 SME, ensuring that the technical development is grounded in practical application and commercial viability across 6 European countries.
Contact Fundacio Hospital Universitari Vall d'Hebron - Institut de Recerca
Contact SciTransfer to explore licensing opportunities for the Federated Learning stroke platform.
