Cancer
AI-human task-sharing could cut mammography screening costs by up to 30 per cent
The most effective way to harness the power of AI when screening for breast cancer may be through collaboration with human radiologists — not by wholesale replacing them, says new research.
The study finds that a “delegation” strategy, where AI helps triage low-risk mammograms and flags higher-risk cases for closer inspection by human radiologists, could reduce screening costs by as much as 30 per cent without compromising patient safety.
The findings could help shape how hospitals and clinics integrate AI into their diagnostic workflows amid a growing demand for early breast cancer detection and a shortage of radiologists, said Mehmet Eren Ahsen, a professor of business administration and Deloitte Scholar at University of Illinois Urbana-Champaign.
“We often hear the question: Can AI replace this or that profession?” Ahsen said. “In this case, our research shows that the answer is ‘Not exactly, but it can certainly help.’ We found that the real value of AI comes not from replacing humans, but from helping them via strategic task-sharing.”
The study, which was published by the journal Nature Communications, was co-written by Mehmet U. S. Ayvaci and Radha Mookerjee of the University of Texas at Dallas; and Gustavo Stolovitzky of the NYU Grossman School of Medicine and NYU Langone Health.
The researchers developed a decision model to compare three decision-making strategies in breast cancer screening: an expert-alone strategy — the current clinical norm in which radiologists read every mammogram; an automation strategy, in which AI assessed all mammograms without human oversight; and a delegation strategy, in which AI performed an initial screening and referred ambiguous or high-risk cases to radiologists.
The model accounted for a wide range of costs, including implementation, radiologist time, follow-up procedures and potential litigation. It evaluated outcomes using real-world data from a global AI crowdsourcing challenge for mammography, which was sponsored as part of the White House Office of Science and Technology Policy’s Cancer Moonshot initiative of 2016 to 17.
The researchers found that the delegation model outperformed both the full automation and the expert-alone approaches, yielding up to 30.1 per cent in cost savings, according to the paper.
While the idea of fully automating radiological tasks may seem appealing from an efficiency standpoint, the study cautions that current AI systems still fall short of replacing human judgment in complex or borderline cases.
“AI is excellent at identifying low-risk mammograms that are relatively straightforward and easy to interpret,” said Ahsen, also the health innovation professor at the Carle Illinois College of Medicine.
“But for high-risk or ambiguous cases, radiologists still outperform AI. The delegation strategy leverages this strength: AI streamlines the workload, and humans focus on the toughest cases.”
With nearly 40 million mammograms performed annually in the U.S. alone, breast cancer screening is a critical public health tool. Yet the process is time-intensive and costly, in both labor and follow-up procedures triggered by false positives. And when cancers are missed, the resulting false negatives can lead to significant harm for patients and health care providers, Ahsen said.
“One of the issues in mammography is, because of the sheer number of screenings performed, that it generates so many false positives and false negatives,” Ahsen said. “If you have a 10% false positive rate out of 40 million mammograms per year, that’s four million women who are being recalled to the hospital for more appointments, screenings and tests, and potentially biopsies.”
That whole process only increases stress and anxiety for the patient, Ahsen said.
“It’s a nightmare scenario,” he said. “Follow-up appointments often take weeks, leaving patients with a black cloud hanging over their heads. It’s a very stressful time for them.”
With AI and the delegation model, it’s possible that health care providers could streamline the process.
“You get screened, AI sees something it doesn’t like and immediately flags you for follow-up, all while you’re still at the hospital,” Ahsen said. “It has the potential to be that much more efficient of a workflow.”
The research also raises broader questions about how AI should be implemented and regulated in medicine.
“The delegation strategy works best when breast cancer prevalence is either low or moderate,” Ahsen said.
“In high-prevalence populations, a greater reliance on human experts may still be warranted. But an AI-heavy strategy also might work well in situations where there aren’t a lot of radiologists – in developing countries, for example.”
Another potential landmine involves legal liability. If AI systems are held to stricter liability standards than human clinicians, then “health care organisations may shy away from automation strategies involving AI, even when they are cost-effective,” Ahsen said.
The findings are potentially applicable to other areas of medicine such as pathology and dermatology, where diagnostic accuracy is critical, but AI is potentially able to improve workflow efficiency.
With the infinite work capacity of AI, “we can use it 24/7, and it doesn’t need to take a coffee break,” Ahsen said.
“AI is only going to continue to make inroads into health care, and our framework can guide hospitals, insurers, policymakers and health care practitioners in making evidence-based decisions about AI integration.
“We’re not just interrogating what AI can do – we’re asking if it should do it, and when, how and under what conditions it should be deployed as a tool to help humans.”
The Femtech World Awards are celebrating the innovators revolutionising the way we diagnose and treat cancer in women.
Cancer is a major public health and economic issue.
Female breast cancer is the most commonly diagnosed cancer in the world, with an estimated 2.3 million cases diagnosed globally in 2020 alone.
However, what once seemed impossible in cancer research is now a reality thanks to a number of technological innovations that have led to breakthroughs in the ways we diagnose, understand and treat cancer.
Through the Women’s Cancer Innovation Award, Femtech World aims to shine a light on the organisations devoted to transforming the future of cancer care for women worldwide.
The Women’s Cancer Innovation Award is one of 10 categories open for entry, all of which seek to acknowledge excellence in femtech and reward the dedication, commitment and innovation of those working in the space.
The Women’s Cancer Innovation Award is sponsored by Endomag.
Endomag believes everyone deserves a better standard of cancer care – that’s why they design their cancer localisation technologies with both the clinician and patient in mind.
Many leading hospitals across the world use their unique solutions to help breast cancer patients avoid surgery when it isn’t needed, and experience better outcomes when it is.
Their Magseed marker is a tiny, non-radioactive seed, ideal for accurately marking tumours and lymph nodes, while the Magtrace lymphatic tracer is the world’s first, long-lasting, non-radioactive dual tracer for lymphatic mapping.
Paired with the Sentimag localisation platform, they have now been widely proven across over 200 clinical studies, featuring more than 20,000 patients.
Entry for the Women’s Cancer Innovation award and all other categories closes on April 17.
Find out more and enter for free here.
More than three million cells have been mapped, showing how breast tissue changes with age, with the biggest shifts seen during menopause.
The research, described as the most detailed map of its kind so far, shows that as women age, all types of cells in breast tissue become fewer, those cells divide less often, and the tissue itself changes.
Together, these shifts create what the researchers call a “micro-environment”, meaning a local tissue setting in which cancer cells may find it easier to take hold.
Breast cancer is the most common cancer in women, accounting for 15 per cent of all new cases.
Four out of five cases occur in women over 50, and as many as one in seven women will develop breast cancer in their lifetime.
The study was led by scientists at the Universities of Cambridge and British Columbia.
The team used advanced imaging techniques to analyse breast tissue from more than 500 women aged 15 to 86, including biopsies taken for non-cancer-related reasons.
Pulkit Gupta from the Cancer Research UK Cambridge Institute at the University of Cambridge, joint first author, said: “Even though breast cancer affects well over 2 million women worldwide, we understand very little about why and when it occurs. As cells divide and replicate, they accumulate mutations that can drive cancer, but why is it that the body can get rid of these mutated cells when we’re younger, but struggles later in life?”
By combining the images with data on hormone receptors, immune cells and tissue architecture, the team mapped how breast tissue changes over time in unprecedented detail.
The findings point to reasons why breast cancer risk rises with age and why tumours in younger women differ biologically.
Gupta added: “Our map revealed that as women age, their breast tissue goes through major changes, with the most dramatic changes occurring at menopause.
“There are changes, too, during their twenties, possibly linked to pregnancy and childbirth, but these are far less pronounced.”
The map showed that milk-producing structures known as lobules shrink or disappear, while ducts, the channels that carry milk, become relatively more common.
The supporting layer around the ducts becomes thicker, fat cells increase and blood vessels decrease.
Changes were also seen in the immune environment. Younger breast tissue contains more B cells and active T cells, immune cells that help identify and kill cancer cells.
As tissue ages, these decline and are replaced by other immune cells linked to a more inflammatory and potentially less protective environment.
Co-senior author Dr Raza Ali from the Cancer Research UK Cambridge Institute at the University of Cambridge said: “We don’t know for certain why the types of immune cell change.
We can speculate that one reason may be because breast milk contains a high concentration of immunoglobulins, probably to help build the infant’s immunity, and these are produced by B cells.
At the same time, cells begin to interact with each other less. Immune cells and stromal cells, which form a supportive scaffold within tissue, become physically more distant from epithelial cells, the specialised cells lining the mammary ducts and lobules that produce and transport milk.
This may make it easier for pre-cancerous cells to escape control.
Co-senior author professor Samuel Aparicio from BC Cancer, University of British Columbia, Canada, said: “We’ve previously seen that age-dependent changes in oestrogen activity occur strongly in milk secreting cells of the breast and now we can see the surprising extent of changes in all cell types, including the immune system, with age.
“We are now seeking to understand the relationship between changes in immune cells and surveillance of early mutations that can arise in milk secreting cells over time.”
Dr Ali added: “It isn’t surprising that we should see fewer epithelial cells, as these play a role in producing breast milk, something that becomes less important with age, but the sheer scale of changes across the breast surprised us.
“What is clear from our map is that all of these changes create an environment where cancer cells that emerge naturally find it easier with age take hold and spread.”
HRT patches used for menopause may be as effective as injections at preventing prostate cancer spread, a study suggests.
Patches that lower testosterone by delivering oestradiol, a form of oestrogen, through the skin were found to be as effective as injections at stopping the cancer from spreading.
Researchers at University College London investigated whether the patches could match the effectiveness of current injection-based hormone therapies.
These injections are routinely given to men with locally advanced prostate cancer, where the disease has spread just beyond the gland.
The main aim of this hormone therapy is to suppress testosterone levels, a hormone that is crucial for the cancer’s growth.
The study, published in the New England Journal of Medicine, involved 1,360 men with an average age of 72, recruited from cancer centres across the UK.
Participants were either given patches to wear or received injections designed to block testosterone production, allowing researchers to compare the effectiveness of the two methods.
The patches used in the trial are the same as those used in hormone replacement therapy, or HRT, to treat menopause symptoms in women.
Researchers found the patches were just as effective as injections at preventing the cancer from spreading.
The patches also led to fewer side effects than injections, which can include hot flushes, bone density problems and risk factors for heart disease such as higher cholesterol, higher blood sugar and higher blood pressure.
However, the patches were linked to more breast tissue swelling.
Experts said patients who are given injections of LHRH agonists, a type of hormone therapy, need multiple hospital or GP visits, while oestradiol patches can be applied by patients at home.
Ruth Langley, from the MRC Clinical Trials Unit at UCL and lead author of the study, said: “We believe our findings should lead to men with locally advanced prostate cancer being able to choose which hormone therapy suits them best.
“For some men, for instance, hot flushes can be very debilitating, and so the patches could greatly increase their quality of life.”
Commenting on the study, Caroline Geraghty, senior specialist nurse manager at Cancer Research UK, said: “Thanks to research, over eight in 10 men diagnosed with prostate cancer will now survive for 10 years or more, as well as finding more effective treatments, we need to find ways to make them kinder too.
“This trial has done exactly that, it shows that hormone patches are just as effective as traditional injections at controlling locally advanced prostate cancer, while being much easier and gentler to administer.
“This should give men greater choice over their treatment in the future, allowing them to live not just longer lives, but better lives.”
The results were published as the UK national screening committee, which advises the Government, prepared to meet to decide the future of screening men for prostate cancer.
In a draft recommendation last year, it rejected population-wide screening using the prostate specific antigen, or PSA, test, saying it ‘is likely to cause more harm than good’.
The committee recommended only screening men with BRCA1 and BRCA2 genetic mutations, who are at much higher risk of prostate cancer, every two years between the ages of 45 and 61.
Health secretary Wes Streeting said he was surprised by the move but that any final decision needs to be ‘based on science and evidence, not on politics’.
Diagnosis4 weeks agoBlood test shows promise in endometriosis
Insight4 weeks agoWomen’s health leaders warn of censorship
Insight4 weeks agoBlood test predicts dementia 25 years before symptoms begin
Menopause4 weeks agoStudy reveals hidden menopause tech privacy concerns
News3 weeks agoFemtech World Awards announces deadline extension
News3 weeks agoLuna and Kindbody partner to bring data-driven insight to women’s health and fertility care
News4 weeks agoPregnancy may shed brain’s grey matter to prepare women for motherhood – study
Menopause4 weeks agoNon-hormonal menopause pill approved for NHS use