Atrial Fibrillation (AF) is the most common arrhythmia worldwide affecting an estimated 5% of people over the age of 65 and is a leading cause of stroke and heart failure. Identification of patients at risk allows preventative measures and treatment before these complications occur. Conventional risk prediction models are static, do not have flexibility to incorporate dynamic risk factors and possess only modest predictive value. Artificial intelligence and machine learning-powered health virtual twin technology offer transformative methods for risk prediction and guiding clinical decisions.

In this prospective observational study, 1200 patients will be recruited in two tertiary centres. Patients hospitalised with acute illnesses (sepsis, heart failure, respiratory failure, stroke or critical illness) and patients having undergone high-risk surgery (major vascular surgery, upper gastrointestinal surgery and emergency surgery) will be monitored with a patch-based remote wireless monitoring system for up to 14 days. Clinical and electrocardiographic data will be used for modelling the risk of new-onset AF. The primary outcome is episodes of AF >30 s and will be described as ratio of episodes/patient and as percentage of patients having episodes of AF. Secondary outcomes include 30-day and 90-day readmission rates and complications of AF.

The aim of this study is to generate data for the development and validation of health virtual twins predicting onset of AF in an at-risk population. The intelligent monitoring to predict atrial fibrillation (NOTE-AF) study is part of the TARGET project, a Horizon Europe funded programme which includes risk prediction, diagnosis and management of AF-related stroke (https://target-horizon.eu/).

The study has received approval by the Health Research Authority and the National Research Ethics Service (REC reference 24/NW/0170, IRAS project ID: 342528) in the UK and has been registered on clinicaltrials.gov (NCT06600620). Results will be disseminated as outlined in the TARGET protocol to communicate project ideas, activities and results to diverse audiences.

NCT06600620.

Atrial fibrillation (AF) is the leading cause of cardioembolic stroke and is associated with increased stroke severity and fatality. Early identification of AF is essential for adequate secondary prevention but remains challenging due to its often asymptomatic or paroxysmal occurrence. Artificial intelligence (AI) offers new possibilities by integrating biomarkers, clinical phenotypes, established risk factors and imaging features to define a personalised ‘digital twin’ model. The TAILOR study aims to (1) examine prospective detection of AF using monitoring devices, (2) investigate novel prognostic MRI markers in patients with an AF-related stroke (AFRS) and (3) validate AI-based models for outcome prediction in AFRS.

This prospective multicentre observational cohort study includes patients aged 40 years and above, with neuroimaging-confirmed diagnosis of ischaemic stroke, recruited from two sites: Hospital del Mar Barcelona (Spain) and Radboud University Medical Centre (The Netherlands). For the first sub-study (n=300), patients will undergo clinical assessment at baseline, 3 months and 12 months, and patch-based or Holter cardiac monitoring. The second sub-study (n=200) involves repeated brain MRI and cognitive examination after AFRS. Finally, AI-driven ‘digital twin’ models developed on retrospective TARGET datasets will be prospectively evaluated in TAILOR using temporal and centre-stratified analyses for advanced predictive tools for AF and AFRS outcomes.

The TAILOR study was approved by local ethics boards in Barcelona (CPMP/ICH/135/95) and Medical Research Ethics Committee Oost-Nederland (NL86346.091.24). Patients will be included after providing informed consent. Study results will be presented in peer-reviewed journals and at global conferences.