The NHS is launching the world’s biggest trial of artificial intelligence to detect breast cancer, which could lead to faster diagnosis of the disease.
AI will be deployed to analyse two-thirds of at least 700,000 mammograms done in England over the next few years to see if it is as accurate and reliable at reading scans as a radiologist.
If it proves successful, hospitals may no longer need to use two radiologists to study every mammogram for signs of breast cancer – the “second reader” system designed to ensure nothing is missed.
Instead, it may be safe to have just one radiologist reading the scan, with AI offering a second opinion. If that happens, it would free up many specialist doctors to do other work – and shorten the time patients have to wait to hear the outcome of diagnostic tests such as X-rays and MRIs.
The Department of Health and Social Care (DHSC) unveiled the trial, alongside confirmation that it is drawing up a new dedicated cancer plan to improve diagnosis and treatment, to mark World Cancer Day on Monday.
A previous smaller study of AI and breast cancer in Sweden in 2023, involving about 80,000 women, found that AI is safe to use, can reduce radiologists’ workload by around half and does not lead to an increase in “false positives” – erroneous detections of symptoms of the disease.
In the new trial, five different sorts of AI will read about 462,000 of the 700,000 mammograms done at 30 breast cancer screening centres, starting later this year. The other 238,000 scans will be read in the usual way by two radiologists and the two sets of results compared.
“This landmark trial could lead to a significant step forward in the early detection of breast cancer, offering women faster, more accurate diagnoses when it matters most,” said Prof Lucy Chappell, the DHSC’s chief scientific adviser and chief executive of the National Institute for Health and Care Research, which is funding the £11m study.
Samantha Harrison, the head of strategic evidence at Cancer Research UK, said: “More cancer cases are diagnosed every year, and innovations like this could help reduce pressure on NHS staff and cut waiting lists. We need more research to understand how AI could help with cancer screening, so it’s fantastic to see the UK government funding this trial.”
Prof Katharine Halliday, the president of the Royal College of Radiologists, said AI has “immense potential” to help doctors manage the growing demand for diagnostic tests, cancer care and the NHS as a whole.
“However, while AI holds great promise, it also carries major risks”, she added, acknowledging concerns that AI algorithms would need to be very carefully designed so they produce equally reliable results for different groups of women regardless of their ethnic background.
She also voiced concern that, while the trial is not due to produce results for several years, the longstanding shortfall in consultants in the NHS is expected to reach 40% by 2028.
Wes Streeting, the health secretary, said he will publish a detailed national cancer plan that is intended to “unleash Britain’s potential as a world leader in saving lives from this deadly disease”.
The Guardian disclosed in September that he was considering doing so, in a break from the Conservatives’ controversial decision to publish a “major conditions strategy”, covering all the major killers, instead of separate strategies for specific diseases.