AI-based tools to help diagnose, treat and predict stroke outcomes across multiple hospitals
Official title: Unleashing a CoMprehensive, Holistic and Patient Centric Stroke Management for a Better, Rapid, AdvancEd and PersonaLised Stroke Diagnosis, TreAtment and Outcome Prediction (UMBRELLA) - Prospective Clinical Study
Run by Hospital Universitari Vall d'Hebron Research Institute · NCT07924371 · Data updated 2026-11-12
This study tests AI-powered tools on real-world stroke patients to see if they can improve pre-hospital triage, diagnosis, and outcome prediction while data stay securely within each hospital.
Quick facts
| Study type | Observational |
|---|---|
| Ages | 18 Years and up |
| Sex | All |
| Enrollment | 10000 (estimated) |
| Sponsor | Hospital Universitari Vall d'Hebron Research Institute Academic / other |
| Locations | 7 sites (Leuven and 6 other locations) |
| Status | Recruiting |
| Started | September 28, 2026 |
| Main results expected | September 30, 2029 |
| Study ends | September 30, 2029 |
| Registry record updated | November 9, 2026 |
| Trial ID | NCT07924371 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a good fit
Adults 18 years or older with a clinical suspicion of acute stroke or TIA who can provide informed consent or have a legally authorized representative.
✕Probably not a fit
Patients not fitting into the specific sub-studies or whose data do not contribute to the AI models may not directly benefit.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
What this trial studies
This is a multicentre, prospective observational study involving seven university hospitals across six European countries. It collects routine clinical, imaging, lab, ECG, and patient-reported data, then harmonises these data to the OMOP Common Data Model. AI models are trained and validated using a federated learning approach so patient data never leave the hospital sites. A retrospective data harmonisation phase precedes prospective validation to test the models on new, independently collected data. The study includes sub-projects focused on pre-hospital triage, rapid reperfusion decisions, emergent intracerebral hemorrhage management, and other stroke-related outcomes.
Why it matters
Potential benefit: If successful, the AI tools could streamline stroke workflows, improve triage accuracy, and enhance treatment decisions without compromising patient privacy.
How similar studies have gone: Federated, data-harmonised AI approaches in stroke care have shown promise in earlier studies, though this exact multicentre federated setup is innovative.
Who can join: the full rules
Show full inclusion / exclusion criteria
Inclusion Criteria: * Age 18 years or older * Clinical suspicion of acute stroke (including TIA) * Written informed consent from the patient or, when not possible, from next of kin; deferred consent is accepted because of the acute setting Additional inclusion criteria by sub-study: * WP2 and WP3: suspected stroke according to ambulance personnel or confirmed LVO stroke, AND symptom onset (or last seen well, if unwitnessed) less than 24 hours earlier * WP4: intracerebral hemorrhage, regardless of sex, risk factors or etiology * WP5: NIHSS below 7 AND premorbid mRS below 4 * WP6: acute ischemic stroke, with or without atrial fibrillation Exclusion Criteria: \* None
Where it's running
-
University Hospitals Leuven - KU Leuven
Leuven, Belgium Recruiting -
Hospital Universitari Vall d'Hebron - Vall d'Hebron Institut de Recerca
Barcelona, Spain Recruiting -
Universitätsklinikum Hamburg-Eppendorf
Hamburg, Germany Not yet recruiting -
Fondazione Policlinico Universitario Agostino Gemelli IRCCS
Rome, Italy Not yet recruiting -
Amsterdam University Medical Centers
Amsterdam, Netherlands Not yet recruiting -
Erasmus MC University Medical Center Rotterdam
Rotterdam, Netherlands Not yet recruiting
Show 1 more location
-
University Hospital Basel
Basel, Switzerland Not yet recruiting
Study contacts
- Study coordinator: Carlos Molina
- Email: carlosav.molina@vallhebron.cat
- Phone: +34 677 189 246
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
Heart assessment to check repeat-stroke risk in people with atrial fibrillation
This project will test whether detailed heart examinations can find which people with atrial fibrillation who just had an ischemic stroke are at high risk of having another stroke.
-
Emergency Stroke Unit for treating acute strokes
This study is testing a new Emergency Stroke Unit that uses a mobile MRI to see if it can help treat stroke patients faster and improve their recovery.
-
Stroke prevention in ischemic stroke with covert atrial fibrillation
This trial tests whether starting apixaban or aspirin after a recent ischemic stroke with suspected but undetected atrial fibrillation can prevent future strokes.
-
Using apixaban to prevent strokes in patients with severe kidney disease and atrial fibrillation
This study is testing if the blood thinner apixaban can help prevent strokes in people with severe kidney disease and atrial fibrillation.
-
Using mobile technology to manage cardiovascular risks in stroke patients
This study is testing if using mobile technology to monitor blood pressure and check for heart rhythm problems can help stroke patients manage their cardiovascular risks better than standard care.
-
Ear-based nerve stimulation to help sleep after a stroke
A device that delivers vagal nerve stimulation through the ear is tested to see if it helps stroke patients in rehab sleep better.
How to take part
- Review the eligibility criteria above with your treating physician.
- Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
- Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.