Almost 2,000 people have taken part in a pilot in West Yorkshire aiming to identify people at risk of developing atrial fibrillation (AF).
AI algorithm, FIND-AF searches patient GP records for any “red flags” that suggest the patient is at risk of developing AF in the next six months, before further testing is offered to confirm the diagnosis. The aim of the trial was to investigate the algorithm and “lay the groundwork for a UK-wide trial” in hopes of improving early diagnosis of AF and “prevent more avoidable strokes”.
The algorithm has been implemented at several GP surgeries in West Yorkshire, thanks to funding from British Heart Foundation and Leeds Hospitals Charity. Those who have been identified as at risk of AF are offered at-home testing and sent a handheld ECG machine. They are then asked to take “two readings a day for four weeks, as well as any time they feel palpitations”. If the results reveal that they have AF, their GP is informed for further discussion of treatment options.
It’s estimated that AF contributes to “around 20,000 strokes each year” in the UK with more than 1.6 million people having already been diagnosed with AF and “many thousands more” who remain undiagnosed.
“All too often, the first sign that someone is living with undiagnosed atrial fibrillation is a stroke,” Professor Chris P Gale, honorary consultant cardiologist at Leeds Teaching Hospitals NHS Trust commented. “Our FIND-AF digital diagnostic and treatment care pathway supports Government’s ambition of moving from treating illness to preventing it. We’re now looking to partner with the NHS and other providers to accelerate its use more widely.”
Clinical trials and research: the wider trend
Norfolk and Norwich University Hospitals alongside the University of East Anglia have been working together to develop the Continuous Ambulatory Vestibular Assessment (CAVA) device to help with identifying the most common causes of dizziness. Patients across the country have been testing the device, which is capable of analysing hours of eye and head movement data to help “speed up the diagnosis” of dizziness.
A research study involving 350 experts from 58 countries has offered recommendations to ensure inclusivity of datasets for training medical AI systems, in an effort to allow “everyone in society to benefit from technologies which are safe and effective”. This has resulted in the collection of input from international experts on 29 consensus recommendations.
In December, we reported on The National Institute for Health and Care Research awarding a £1.3 million grant to four South East London based organisations to work on a research project for a digital weight management tool. It was part of seven new research projects funded by the NIHR Invention for Innovation (i4i) Programme, focused on the development of medical devices, in vitro diagnostic devices and digital health technologies, addressing existing or emerging needs.
