Artificial intelligence (AI) could be used to identify patients at risk of heart failure, meaning they could be treated sooner, Leeds-based researchers have said.
An algorithm, known as Find-HF, was ‘trained’ by researchers at the University of Leeds to detect early symptoms of the disease using patient records.
According to the British Heart Foundation (BHF), more than a million people currently suffer from heart failure in the UK.
Professor Chris Gale, from Leeds Teaching Hospitals NHS Trust and the University of Leeds, said the technology would open a “crucial window of opportunity” for patients.
For the study, funded by the BHF, researchers used patient records from 565,284 UK adults to train the AI algorithm,
It was then tested on a database of 106,026 records from National Taiwan University Hospital.
The AI was able to accurately predict which patients were at highest risk of developing heart failure and which might be admitted to hospital with the condition within five years, the researchers said.
Professor Gale, consultant cardiologist, said: “This is an extremely powerful and unique national resource, and it is time to use this data for the benefit of patients.
“Find-HF could potentially advance diagnostics by two years.”
The researchers suggested the platform could be used by GPs as an early warning system, allowing them to test and diagnose patients earlier.
Dr Ramesh Nadarajah, a UK health data researcher at the University of Leeds, said: “Many people are diagnosed with heart failure too late, when disease-modifying treatments are potentially less effective, particularly women and the elderly.
“We use machine learning tools with regularly collected data to identify people with heart failure earlier, so they can get the right treatment, avoid hospitalizations and deaths, and improve their quality of life. “
Follow BBC Yorkshire on Facebook, X (formerly Twitter) And Instagram. Send your story ideas to yorkslincs.news@bbc.co.uk.
