Artificial intelligence can save NHS time and money with heart scans

We’re going to be seeing more AI tools in medicine as it is introduced into further areas of medical practice. There’ll be none more important than that devised by Sheffield University scientists to speed up the diagnosis of heart disease. Astonishingly, they’ve got it down to just one minute.

To assess a patient’s heart function, doctors typically use MRI heart scans to give information on how the heart is pumping so diagnosis can be made, and treatments started or adjusted.

However, the current process for assessing these results is labour intensive and time consuming.

Cardiac imaging specialists first have to draw contours of the heart on the scans and then do complex mathematical calculations to work out blood flow in and out of the heart.

Around 10 to 20 MRI cardiac scans a day are usually processed at a workstation by a radiologist.

Sheffield researchers reckon their AI tool will save doctors up to 30 minutes per scan, freeing up NHS resources while also helping earlier diagnoses. They say the new software can provide a diagnosis in just 60 seconds.

Their pioneering AI tool, which provides a quick and comprehensive analysis of the heart’s function, could improve care of heart disease not only with faster diagnosis but also with more detailed information about the heart’s function.

The tool works by automatically detecting chambers of the heart on images taken from MRI heart scans – and performs this task quickly.

Consultant cardiothoracic radiologist at Sheffield Teaching Hospitals, Dr Andrew Swift, says: “Getting answers quickly and accurately will reduce even further the time it takes for patients to begin receiving the right treatment.

“Obtaining complex measurements showing how well both the left and right side of the heart are pumping is a time-intensive manual task.

“[The software] has the potential to free up hospital staff to deal with more patients rather than spend time on image analysis.”

The technology has been extensively tested on thousands of images and validated in more than 5,000 Sheffield MRI scans, plus further tests on scans from over 30 hospitals in the UK.

The team aims to make it available to the wider NHS thanks to a £5,000 prize from a Medipex NHS Innovation Award.

Sheffield’s Professor Wendy Tindale OBE said: “We are delighted that the talents of our scientific and clinical teams in identifying and looking for solutions for healthcare problems have been recognised in this prestigious regional awards scheme.”