TRUSTroke

Artificial intelligence to optimise stroke treatment.

The TRUSTroke project proposes a novel platform based on artificial intelligence, trustworthy by design and privacy-preserving, to assist clinicians, patients and caregivers in the management of acute and chronic phases of ischemic stroke.

The project is based on the integration of clinical and patient-reported data, outcomes and experiences for a trustworthy assessment of disease progression and risks, enabling more personalised and effective stroke management, as well as providing inter-hospital benchmarking and sharing of best practices.

TRUSTroke addresses risks of clinical severity at discharge; clinical worsening leading to unplanned hospital readmissions; poor mobility, incomplete recovery and unfavorable clinical long-term outcomes; and stroke recurrence.

With this goal, a federated learning infrastructure will enable multiple clinical sites to build several trustworthy AI-based predictive models by leveraging stroke data without compromising privacy and implementing best-in-class security and privacy protocols.

FAIRified clinical data from leading European hospitals and outpatient monitored data from a remote home-care system will be used to train and validate trustworthy AI models for stroke prediction, as well as to personalise the patients’ assessment of cardiovascular risk factors, treatment compliance and communication with healthcare professionals.

The TRUSTroke platform will be trustworthy by design as it will comply with recognized guidelines for building FAIR resources and trustworthy AI systems, including the need for transparency, explainability, robustness, accountability, accuracy and security of learned AI models.

TRUSTroke will conduct a series of user experience studies to increase the usability of the platform and improve communication to the end-users, as well as a final proof-of-concept clinical study.

Eurecat participates in the TRUSTroke project through its Digital Health Unit, which develops artificial intelligence models that are characterized by their reliability and trust. In addition, the Unit is responsible for the deployment of data infrastructures in the various European hospitals involved.

The TRUSTroke consortium is made up of 13 partners from six European countries.