Related Experiment Video
Updated: Dec 4, 2025
Estimating Bilateral Atrial Function by Cardiovascular Magnetic Resonance Feature Tracking in Patients with Paroxysmal Atrial Fibrillation
Published on: July 20, 2022
Identification of undiagnosed atrial fibrillation patients using a machine learning risk prediction algorithm and
Nathan R Hill1, Chris Arden2, Lee Beresford-Hulme3
1Bristol Myers Squibb Pharmaceutical Ltd, Uxbridge, UK.
Insights
A new machine learning algorithm effectively identifies individuals at high risk for atrial fibrillation (AF). This tool, combined with ECG monitoring, aims to improve early detection of AF in primary care settings.
Area of Science:
- Cardiology
- Medical Informatics
- Public Health
Background:
- Atrial fibrillation (AF) significantly increases stroke risk and severity but is often asymptomatic, leading to delayed diagnosis.
- Current AF screening methods are limited by cost-effectiveness and diagnostic sensitivity.
- Novel approaches are needed for efficient population-level AF screening.
Purpose of the Study:
- To evaluate the effectiveness of a machine learning-based AF risk prediction algorithm integrated with diagnostic testing in primary care.
- To assess the algorithm's ability to identify high-risk individuals for targeted AF screening.
- To compare AF diagnosis rates between an intervention group using the algorithm and a control group.
Main Methods:
- A randomized controlled trial involving participants aged 30+ without diagnosed AF from UK general practices.
- Intervention group: risk stratification using a machine learning algorithm (risk score ≥ 7.4%) followed by 12-lead ECG and 2-week KardiaMobile monitoring.
- Control group: routine care for comparison.
Main Results:
- Primary outcome: comparison of AF diagnosis incidence between intervention and control arms.
- Secondary analysis: evaluation of the algorithm's predictive performance in a real-world setting.
- Data collected from a large UK dataset (2,994,837 patients) for algorithm development.
Conclusions:
- Successful implementation could enable targeted AF screening in primary care, focusing resources on high-risk populations.
- The study aims to demonstrate improved AF identification rates through algorithm-guided screening.
- This approach holds potential for broader adoption in primary care to mitigate AF-related complications.
Abstract:
Atrial fibrillation (AF) is associated with an increased risk of stroke, enhanced stroke severity, and other comorbidities. However, AF is often asymptomatic, and frequently remains undiagnosed until complications occur. Current screening approaches for AF lack either cost-effectiveness or diagnostic sensitivity; thus, there is interest in tools that could be used for population screening. An AF risk prediction algorithm, developed using machine learning from a UK dataset of 2,994,837 patients, was found to be more effective than existing models at identifying patients at risk of AF. Therefore, the aim of the trial is to assess the effectiveness of this risk prediction algorithm combined with diagnostic testing for the identification of AF in a real-world primary care setting. Eligible participants (aged ≥30 years and without an existing AF diagnosis) registered at participating UK general practices will be randomised into intervention and control arms. Intervention arm participants identified at highest risk of developing AF (algorithm risk score ≥ 7.4%) will be invited for a 12‑lead electrocardiogram (ECG) followed by two-weeks of home-based ECG monitoring with a KardiaMobile device. Control arm participants will be used for comparison and will be managed routinely. The primary outcome is the number of AF diagnoses in the intervention arm compared with the control arm during the research window. If the trial is successful, there is potential for the risk prediction algorithm to be implemented throughout primary care for narrowing the population considered at highest risk for AF who could benefit from more intensive screening for AF. Trial Registration: NCT04045639.
