Machine Learning and Artificial Intelligence for Early Detection of Stroke and Atrial Fibrillatio
- Conditions
- atrial fibrilation10007521
- Registration Number
- NL-OMON56279
- Lead Sponsor
- Kompetenznetz Vorhofflimmern e.V./Atrial Fibrillation NETwork (AFNET)
- Brief Summary
Not available
- Detailed Description
Not available
Recruitment & Eligibility
- Status
- Pending
- Sex
- Not specified
- Target Recruitment
- 150
1. Patients with paroxysmal AF (clinically defined as AF episodes less than one
week), or
patients with persistent AF (clinically defined as AF episodes longer than one
week),
or patients with permanent AF (no documented sinus rhythm or possibility to
restore sinus rhythm by any means).
2. Patient (or legally acceptable representative if applicable) provides
written Informed Consent to participate in the study. The patient has the
option to give separate consent to donate extra volume of blood during routine
blood collection, that can be used for biomedical research.
3. Patient is at least 18 years of age.
4. Patient must own a Smartphone with Apple iOS Version 14.5 (or higher) or
with Android Version 8.0 (or higher).
1. Any disease that limits life expectancy to less than 1 year.
2. All persons unable to provide informed consent.
3. All persons exempt from participation in a study or trial by law.
4. Any medical or psychiatric condition which, in the Investigator*s opinion,
would preclude the participant from adhering to the protocol or completing the
study per protocol.
Study & Design
- Study Type
- Observational non invasive
- Study Design
- Not specified
- Primary Outcome Measures
Name Time Method <p>The general objectives of the MAESTRIA-AFNET 10 study on clinical epidemiology<br /><br>and medical management of atrial fibrillation (AF) are summarized as follows:<br /><br>- Enrolment of a representative cross-section of AF patients in Europe.<br /><br>- Detailed analysis of clinical and relevant parameters (digitalised ECG,<br /><br>cardiac imaging, blood biomarkers) that could be used during clinical practise<br /><br>for the diagnosis of atrial cardiomyopathy and patient*s outcome.<br /><br>- The data sets will be assessed using Artificial Intelligence (AI) algorithms<br /><br>to characterise specific subgroups of AF or define novel outcome predictors.</p><br>
- Secondary Outcome Measures
Name Time Method <p>Potential Outcome Parameters<br /><br>* AA burden and vascular stiffness (measured by Preventicus Heartbeats and a<br /><br>wearable with photoplethysmographic -PPG- sensor to be coupled<br /><br>with a smartphone for continuous heart rhythm monitoring for 12 months).<br /><br>* MoCA Cognitive function test.<br /><br>* EQ-5D-5L Quality of Life questionnaire.<br /><br>* Ischaemic events (systemic, myocardial and cerebral) at 12 months.<br /><br>* Clinically relevant changes in CT/MRI for patients in which CT or MRI is<br /><br>clinically indicated.<br /><br>- ECG analysis<br /><br>- All variables from ECGs, CTs, MRIs & echos will be integrated for final<br /><br>assessment.</p><br>