ITNOW's Popular Computer Science (or PopCompSci) brings the most exciting stories from around the world of computer science together for a taste of the unexpected ways in which tech is impacting our lives. Here, we tell you how a University of Leeds based project shows AI can be effective in helping GPs identify heart failure more quickly, and begin potentially life saving treatment.
A project from the University of Leeds has shown that AI can help GPs detect heart failure more quickly by looking for patterns in patients’ records. Early diagnosis of heart failure can lead to much better outcomes, so it’s hoped that the still-developing system will eventually save lives — particularly among women and older people.
Dr Ramesh Nadarajah, a Health Data Research UK Fellow at Leeds’ School of Medicine, presented the British Heart Foundation funded research at the British Cardiovascular Society Conference in Manchester. He said: ‘Many people receive their diagnosis of heart failure at too late a stage when disease modifying treatments are potentially less effective, especially women and older people. We are using machine learning tools with routinely collected data to identify people with heart failure earlier to get the right treatment, prevent hospital admissions and death, and improve quality of life.’
The team of researchers was led by Chris Gale, Professor of Cardiovascular Medicine at Leeds’ School of Medicine and Consultant Cardiologist at Leeds Teaching Hospitals NHS Trust.
For you
Be part of something bigger, join BCS, The Chartered Institute for IT.
At the centre of the machine learning systems is an algorithm called FIND-HF. The algorithm was trained to recognise the early symptoms most likely to lead to a heart failure diagnosis using patient records from 565,284 UK adults. It was then further tested on another database of 106,026 Taiwan National University Hospital records.
Professor Chris Gale said: ‘Data is collected about patients in every interaction they have with healthcare. This is an extremely powerful and unique national resource; it is time to use this data to benefit patients. FIND-HF could potentially bring diagnoses forward by two years, opening a crucial window of opportunity for treatments to make the most difference.’
Next, the researchers plan to test FIND-HF by inviting those identified in primary care records as being at the highest risk to be assessed for heart failure. They hope that in the future, FIND-HF could be routinely used by GPs to determine heart failure risk when patients present with very early symptoms, reducing the time from initial symptoms to diagnosis with a simple push of a button.
