Loading...
Loading...
Browse all stories on DeepNewz
VisitWill Find-AF AI tool be rolled out nationwide in the UK by end of 2025?
Yes • 50%
No • 50%
Announcements from the NHS or British Heart Foundation regarding nationwide implementation
UK's Find-AF Trial Uses AI to Detect Atrial Fibrillation Early
Dec 28, 2024, 11:23 AM
A new artificial intelligence tool is being trialed in the UK to detect atrial fibrillation (AF), a heart condition that can lead to strokes, before symptoms appear. The tool, developed by scientists and clinicians at the University of Leeds and Leeds Teaching Hospitals NHS Trust, analyzes GP records for 'red flags' that indicate a risk of developing AF. The trial, named Find-AF, is funded by the British Heart Foundation (BHF) and Leeds Hospitals Charity. It uses anonymized electronic health records from over 2.1 million people to train the algorithm, which has been validated with data from an additional 10 million records. The tool assesses risk based on factors including age, sex, ethnicity, and other medical conditions. High-risk individuals are offered a handheld electrocardiography (ECG) machine for further monitoring. John Pengelly, a retired Army captain from West Yorkshire, participated in the trial and was diagnosed with AF, which he now manages with medication to reduce his stroke risk. If successful, the trial could lead to a nationwide rollout, potentially preventing thousands of strokes annually, as AF is a contributing factor in around 20,000 strokes each year in the UK.
View original story
No • 50%
Yes • 50%
Neutral • 25%
Unsuccessful • 25%
Moderately successful • 25%
Highly successful • 25%
0-50 hospitals • 25%
More than 150 hospitals • 25%
101-150 hospitals • 25%
51-100 hospitals • 25%
Yes • 50%
No • 50%
Yes • 50%
No • 50%
UK • 25%
USA • 25%
Other • 25%
Germany • 25%
Australia • 25%
United Kingdom • 25%
United States • 25%
Canada • 25%
21-30% reduction • 25%
More than 30% reduction • 25%
Less than 10% reduction • 25%
10-20% reduction • 25%
Age • 25%
Other medical conditions • 25%
Ethnicity • 25%
Sex • 25%