11 March 2022
Just published in the Journal of Cardiovascular Magnetic Resonance an article says an AI test that can detect heart disease in just 20 seconds, with a much higher degree of accuracy than existing methods, will be rolled out in the UK’s National Health Service after a successful pilot.
The tool analyses heart MRI scans as they happen – compared to the 13 minutes it takes for a doctor to check them manually under the existing system.
For now, radiologists using the AI tool will continue to double-check the results and write up the report themselves – but the diagnosis will be completed much quicker as the underlying analysis will have already been done.
This means the typical two to four-week waiting time for the result could be reduced by about a third, as the time freed up by the technology enables radiologists to get to it sooner, according to project leader Dr Rhodri Davies, of University College London and St Bartholomew’s Hospital.
And he predicts that in the next five to 10 years we could see the waiting time speed up even more, as human input may be dropped altogether in favour of an AI-only analysis.
“Our new AI reads complex heart scans in record speed, analysing the structure and function of a patient’s heart with more precision than ever before. The beauty of the technology is that it replaces the need for a doctor to spend countless hours analysing the scans by hand,” Dr Davies said.
Each year, around 120,000 heart MRI scans are performed in the UK. The researchers say that the AI will free up valuable time of healthcare staff – saving around 3,000 “clinician days” every year – so their attention can be directed to seeing more patients on NHS waiting lists, which will ultimately help with the backlog in vital heart care.
The tool diagnoses heart conditions that affect the size and function of the heart muscle, such as heart failure, hypertrophic cardiomyopathy (HCM) – where the heart muscle thickens – and dilated cardiomyopathy (DCM) – when the heart muscle walls become stretched and thin. All of these make it difficult for the heart to pump properly.
Furthermore, it is more accurate than human radiologists at reading the scans, meaning the number of misclassifications under the new system could be about half that of the present system – so many patients would get more suitable treatments, Dr Davies said.
For example, nearly one in seven patients diagnosed with hypertrophic cardiomyopathy (HCM) – a condition for which many benefit from a defibrillator, is misclassified.
Some 6.8 per cent of them are likely to have benefitted from a defibrillator but were not recommended one under the existing system, while 8.7 per cent had one fitted that probably did not need it, Dr Davies said.
These errors could be cut in half under the new system, he added.
The AI tool is being used at University College London Hospital, St Bartholomew’s Hospital and Royal Free Hospital.
It will be rolled out to another 40 hospitals and clinics in the UK, the US and Europe from the summer – and in the next few years Dr Davies hopes it will be introduced much more widely across the NHS.
Dr Sonya Babu-Narayan, associate medical director at the British Heart Foundation, which funded the research, said: “This is a huge advance for doctors and patients, which is revolutionising the way we can analyse a person’s heart MRI images to determine if they have heart disease at greater speed.”
“The pandemic has resulted in a backlog of hundreds of thousands of people waiting for vital heart scans, treatment and care. It’s heartening to see innovations like this, which together could help fast-track heart diagnoses and ease workload so that in future we can give more NHS heart patients the best possible care much sooner.”
Comment
The MHMS in the Solomon Islands could greatly benefit from using the new AI tool given the degree of NCD related heart disease in the country.
It would be my suggestion that the MHMS call on the British High Commission in Honiara to see whether it would be possible for High Commissioner to get the assistance of the British Government in getting the tool for local radiologists at the NRH and possibly in other provincial hospitals.
Yours sincerely
Frank Short
