Artificial intelligence (AI) technologies can be used to help plan the treatment of patients undergoing radiotherapy treatment, following the publication of draft guidance from the National Institute for Health and Care Excellence (NICE).
The move is set to speed up the time it takes to produce ‘contours’ or outlines of the healthy organs so the cancer is targeted while nearby healthy cells are avoided.
This could save money and may allow healthcare professionals to spend more time with patients or concentrate on complex cases when using artificial intelligence (AI) is not appropriate.
The draft guidance says all contours created by AI must still be reviewed by a trained healthcare professional and edited as needed before being used in radiotherapy treatment planning.
A review stage currently takes place for manual contours and early evidence suggests that using AI is quicker than manual contouring, even when including time for healthcare professional review and edits.
Generating the evidence base
More evidence will now be generated to further check that these time savings are realised in practice.
Evidence seen by NICE’s independent medical technologies advisory committee suggests that AI technologies generally produce similar-quality contours of organs at risk as those carried out manually, with most only needing minor edits.
The role imaging plays in radiotherapy treatment planning is quite pivotal, so recommending the use of AI technologies to help support treatment planning alongside clinical oversight by a trained healthcare professional could save both time and money
At present following a CT or MRI scan, a radiographer would mark up, or contour, an image by hand to highlight organs at risk of radiation damage, lymph nodes, and the site of the cancer.
The dose of radiotherapy is then calculated to target the tumour site, but also to prevent organs and healthy tissue from being damaged.
The change to AI automated mark-up is not expected to affect patient outcomes.
Clinical experts advising the independent committee estimated a time saving of 10 minutes to 30 minutes per plan, depending on the amount of editing needed, while the clinical evidence presented to the committee suggests it may range between 3-80 minutes of time saved per plan.
Under pressure
This is the first piece of NICE guidance to recommend the use of AI to aid healthcare professionals in their roles.
Sarah Byron, programme director for health technologies at NICE, said: “NHS colleagues working on the frontline in radiotherapy departments are under severe pressure, with thousands of people waiting for scans.
“The role imaging plays in radiotherapy treatment planning is quite pivotal, so recommending the use of AI technologies to help support treatment planning alongside clinical oversight by a trained healthcare professional could save both time and money.
These tools have the potential to improve efficiency and save clinicians thousands of hours of time that can be spent on patient care
“These technologies could decrease the time required to complete a plan, so they are able to use their expertise planning the most-complex of cases of radiotherapy or free up time to deal with other patient-facing tasks.
“We will continue to focus on what matters most and the recommendations made by our independent committee can help to bring waiting lists down for those needing radiotherapy treatment.”
Health and Social Care Secretary, Steve Barclay, added: “It’s hugely encouraging to see the first positive recommendation for AI technologies from a NICE committee, as I’ve been clear the NHS must embrace innovation to keep fit for the future.
“These tools have the potential to improve efficiency and save clinicians thousands of hours of time that can be spent on patient care.
“Smart use of tech is a key part of our NHS Long Term Workforce Plan, and we’re establishing an expert group to work through what skills and training NHS staff may need to make best use of AI.”
NHS England’s radiotherapy dataset shows that there were 134,419 radiotherapy episodes in England in April 2021 to March 2022, of which a significant proportion require complex treatment planning.
Cost savings
Technology costs ranged from £4-£50 per plan and included software and other associated costs including healthcare professional training.
The possible resource benefits calculated by NICE shows that, if the lowest time saving of three minutes per plan is assumed, and 75,000 plans are generated using AI auto-contouring, the time saved would be 3,750 hours.
This would increase to 52,500 hours for 75,000 plans and a medium time saving of 42 minutes being assumed.
With the NHS under more pressure than ever to curb waiting lists and see to the ever-expanding list of patients in need of care, the use of AI for performing radiotherapy in lung, prostate, and colorectal cancers will hugely support practitioners by freeing up valuable time and helping improve patient care
At the higher end of the scale, 100,000 hours would be saved for 75,000 plans and a time saving of 80 minutes per plan being assumed.
Due to a lack of robust data on current practice and other variables such as the costs and time involved, more evidence needs to be generated over the next three years so a full cost/benefit analysis can be carried out by NICE.
But the publication of the guidance is being widely welcomed by technology leaders.
Industry support
Speaking to BBH, Adrian Sutherland, strategy director for global healthcare at Endava, said: “This is no doubt a step in the right direction for the NHS, which has long suffered from major staffing, resourcing, and funding challenges.
“With the NHS under more pressure than ever to curb waiting lists and see to the ever-expanding list of patients in need of care, the use of AI for performing radiotherapy in lung, prostate, and colorectal cancers will hugely support practitioners by freeing up valuable time and helping improve patient care.
The human in the loop is vital, especially in the healthcare industry, and those implementing AI solutions will need to make sure the human touch is threaded throughout their operations
“Cancer outcomes are much improved with early treatment, so tackling long waiting lists and treating people at an early stage by using AI to automate clinical workflows will quite literally save lives.
“And leading with patient-centric care and automating clinical workflows would mean these illnesses are caught sooner and could alleviate pressure on the NHS not just in the short term, but support with curbing long-term care needs that are caught too late.
“From a standpoint of clinical safety and patient acceptance, such AI applications still need input from medical professionals – in this case radiographers and other attending NHS staff.
“And the human in the loop is vital, especially in the healthcare industry, and those implementing AI solutions will need to make sure the human touch is threaded throughout their operations.”
