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.”
Only one per cent of women can name all five gynaecological cancers, new research suggests, as 21 women in the UK die every day of the diseases.
The report also found that 31 per cent of women have put off or avoided seeking medical advice for gynaecological symptoms.
It also found that 43 per cent of women invited for cervical screening said barriers had put them off attending, while 18 per cent of respondents aged 25 to 34 who had been invited had never attended.
The five main gynaecological cancers are womb, also called uterine, ovarian, cervical, vulval and vaginal cancer.
The Lady Garden Foundation said that, while progress has been made since the UK government’s 2022 Women’s Health Strategy aimed to improve gynaecological cancer care, significant challenges remain.
John Butler, medical director and trustee at the Lady Garden Foundation, said: “The fact that only one per cent of the population can name the diseases that directly affect half of us underscores a significant awareness gap, impacting individuals’ ability to recognise vital signs and symptoms or seek timely medical help.
“Addressing this isn’t just about awareness; it’s a critical public health priority. Our collective efforts are essential to ensure the latest commitments announced by this government translate into tangible change that saves lives.”
The report said key reasons for delaying medical advice included difficulty making appointments, embarrassment and, for cervical screening, fear of pain or previous bad experiences.
Women also reported challenges within healthcare interactions, including feeling “not taken seriously”, “dismissed” or “not believed” when seeking gynaecological advice.
Jenny Halpern Prince, chief executive and charity co-founder, said: “We frequently hear reports of women feeling ‘not taken seriously,’ ‘dismissed,’ or ‘not believed’ when seeking gynaecological advice.
“These experiences highlight crucial areas where we can improve patient support and trust within our healthcare system, ensuring women receive the empathetic and effective care they need.”
The Lady Garden Foundation said it aims to increase awareness of both the charity and the five gynaecological cancers.
It also aims to serve as a primary entry point for reliable, stigma-free information, helping people understand their bodies, recognise symptoms and overcome barriers to accessing care.
Its Silent No More Garden was unveiled at the RHS Chelsea Flower Show 2026. Designed by Darren Hawkes, the garden serves as a national call to action, using five sculptures to spark conversations, break long-standing taboos and encourage open dialogue about symptoms and preventative care.
Butler said: “Continued focus and collaborative action are essential to progress.
“The ongoing commitment from the government, alongside societal efforts to break down taboos surrounding gynaecological health, are crucial.
“The Lady Garden Foundation is dedicated to being a beacon of information and support, empowering women with the knowledge they need. We urge everyone to learn the signs, speak up, and help us save lives.”
AI could transform ovarian care by personalising cancer and fertility treatment, but more clinical validation is needed before routine use.
A systematic review and meta-analysis found AI models showed high diagnostic accuracy for ovarian cancer when combining data such as ultrasound scans and blood test results.
Across 81 studies, AI models correctly identified ovarian cancer in around nine out of 10 cases, with pooled rates of 89 to 94 per cent.
They were also highly accurate at ruling out ovarian cancer when it was not present, with specificity of 85 to 91 per cent.
The analysis also found that explainable AI tools could predict complete surgical cytoreduction in advanced ovarian cancer.
Complete surgical cytoreduction means removing all visible cancer during surgery, which can be an important goal in treatment planning.
The tools achieved a pooled AUC of 0.87. AUC is a measure of how well a model distinguishes between different outcomes, with higher scores showing stronger performance.
In reproductive medicine, AI algorithms helped physicians optimise ovarian stimulation protocols and predict follicular growth during IVF.
Ovarian stimulation is the use of hormones to encourage the ovaries to produce eggs, while follicles are the small sacs in the ovaries where eggs develop.
The review found AI could reliably model ovarian response in IVF with a pooled AUC of 0.81.
However, researchers said challenges remain in translating promising research findings into routine clinical practice.
They identified substantial variation across studies, driven by retrospective study designs, variable AI systems and a lack of standardised validation.
Only 22 per cent of analysed studies reported prospective, multicentre external validation, where models are tested forward in time across multiple healthcare settings.
The authors called for rigorous validation to help close the gap between research and routine clinical practice, alongside standardised methodological and reporting frameworks, smooth integration with clinical workflow and robust governance to support responsible and ethical AI use.
They concluded: “Artificial intelligence is a transformative force in the management of ovarian conditions.
“In gynaecologic oncology, AI enhances every phase of care, from early detection and accurate diagnosis to prognostic stratification and surgical planning.”
In reproductive medicine, AI personalises ovarian stimulation and refines the diagnosis of heterogenous endocrine disorders such as PCOS.
PCOS, or polycystic ovary syndrome, is a hormonal condition that can affect periods, skin, weight and fertility.
Femtech World is delighted to reveal the shortlist for this year’s Women’s Cancer Innovation award.
The award, sponsored by Endomag, will honour a groundbreaking innovation dedicated to the prevention, early detection treatment or ongoing care of cancers that uniquely or disproportionately affect women.
Endomag is a medical technology company devoted to improving the global standard of cancer care.
Its Sentimag system, Magseed marker and Magtrace lymphatic tracer are used by thousands of the world’s leading physicians and cancer centres.
After careful review of this year’s submissions, we are delighted to announce the three shortlisted entries for the Women’s Cancer Innovation Award 2026.
Auria is tackling one of the most stubborn problems in breast cancer screening: the 66 per cent of women who simply don’t participate.
Rather than improving existing imaging pathways, Auria is creating an entirely new access layer: a non-invasive, at-home test that detects protein biomarkers for breast cancer in tears.
Auria’s test, a CLIA-certified Lab Developed Test, has been validated across more than 2,000 patients in multiple clinical studies with collaborators including MD Anderson Cancer Center and Stanford University.
It reports a sensitivity of 93 per cent and a negative predictive value of 98 per cent.
Founded on six years of combined research at the University of Barcelona and UC Irvine, The Blue Box has developed a non-invasive, urine-based test that detects breast cancer by analysing volatile organic compound (VOC) signatures – no radiation, no compression, no imaging facility required.
The test achieves a sensitivity of 88.42 per cent, outperforming mammography by 15 per cent overall, and by 30 per cent specifically in women with dense breasts.
The technology could function as a first-line screening tool in primary care settings, as a complement to mammography for high-density patients, or as an accessible alternative in healthcare systems where imaging infrastructure is limited.
Celbrea is a disposable and affordable thermal screening device that empowers women of all ages to stay on top of monitoring their breast health.
The device aims to add to doctors’ existing standard evaluation protocols with a quick, painless examination. Celbrea does not replace a mammogram but simply provides an additional way to screen for breast disease, including breast cancer.
The device consisting of two disposable pads with photochromic sensors. The pads are self-applied to each breast for 15 minutes.
1188 nano-sensors are embedded within a biocompatible multilayer pad, accurately measuring any temperature differences on the surface of the breast using liquid crystal thermographic technology.
What happens next
The shortlisted entries will now be judge by an Endomag representative who will reveal the winner at a virtual awards event on June 19.
Winners will receive a trophy and will be interviewed by a Femtech World journalist.
Entrepreneur4 weeks agoFuture Fertility raises Series A financing to scale AI tools redefining fertility care worldwide
News4 weeks agoWomen’s digital health market set to reach US$5.28 billion in 2026 – report
Insight4 weeks agoWhy the UK’s fertility rate keeps falling – and what it means if you’re trying now
Wellness3 weeks agoWomen’s HealthX unveils Northwell Health, Corewell Health, Biogen & more to headline Chronic Disease stage
Opinion3 weeks agoWhat Maternal Mental Health Month reveals about where postpartum support actually breaks down
Fertility4 weeks agoToxins and climate harms having ‘alarming’ effect on fertility, research warns
Insight2 weeks agoNIH Grant terminations disproportionately impact minority scientists, research finds
Adolescent health2 weeks agoWUKA brings Period-Positive Pool Party to London Aquatics Centre to keep girls swimming through puberty