search.noResults

search.searching

saml.title
dataCollection.invalidEmail
note.createNoteMessage

search.noResults

search.searching

orderForm.title

orderForm.productCode
orderForm.description
orderForm.quantity
orderForm.itemPrice
orderForm.price
orderForm.totalPrice
orderForm.deliveryDetails.billingAddress
orderForm.deliveryDetails.deliveryAddress
orderForm.noItems
Technology


Building AI for women’s health


Women make up just over half the UK population, yet they often remain a minority in the data that trains AI. At a recent London showcase, clinicians, academics, regulators, founders and investors gathered to ask: how can artificial intelligence be used safely to address clinical challenges in women’s health, and what does the route look like? Dr. Fran Conti-Ramsden and Dr. Nina Sesto share the key findings.


The timing was hard to ignore. In the weeks around this event, Martha’s Rule was extended to all maternity settings in England and the findings of a landmark independent investigation into maternity failures are reverberating through the service. Publication of the renewed Women’s Health Strategy earlier in 2026 is bringing policy focus to health inequalities in women’s health in the UK, with strong focus on women’s voices and choices in their care. Strong emphasis is being placed on the NHS 10-Year Health Plan priorities of digital reform. Innovation is desperately needed, and


many are looking to advances in AI and digital technologies to close these long-standing gaps. Against that backdrop, a room of around 120 people gathered at the London Institute for Healthcare Engineering to consider whether artificial intelligence can help close some of the gaps in women’s health, and, importantly, whether it can be built and regulated in a way we can trust. The half-day showcase, which MEGI Health


convened and sponsored, brought together a broad spectrum of domain experts; Obstetricians & Gynaecologists sat alongside clinical scientists, cybersecurity researchers, innovators, technology and regulatory specialists and venture capital partners. The result was a lively, balanced discussion of both the promise and the challenges of applying AI in women’s health.


Old problems: women are missing from the data The opening framing, set by Prof. Eugene Oteng- Ntim, Professor of Obstetrics & Head of Women’s Services at Guy’s and St Thomas’ Hospital, London, was stark. Women make up roughly 51 per cent of the population but women’s health attracts a small fraction of research and private equity funding, and that imbalance is not academic. It flows directly into the datasets on which modern clinical tools are built. Dr. Elsa Zekeng, founder of SökerData, expanded on this. A large and growing share


of adults now use general-purpose AI as a health adviser, yet the best-performing large language models still answer women’s health questions a little better than a coin toss on some benchmarks. The reason is upstream: data used to train AI inherits all of the biases in the underlying research, including poor representation of women, and this is further compounded when intersectionality with ethnicity is considered. When the foundation is skewed, so is everything built on it. The clinical consequences are already


measurable and long predate AI. Women are significantly more likely than men to be misdiagnosed following a heart attack, in part because symptoms present differently and the evidence base was built largely around men. Black women with breast cancer face substantially worse mortality than their white counterparts. As Dr. Zekeng reminded the room, women were not required to be included in US clinical trials until 1993, and mandated inclusion of ethnic minorities is more recent still (2024). AI does not create these inequities, but trained on existing data and the status quo, it risks scaling them.


New problems - data privacy in women’s health Dr. Ruba Abu-Salma, Senior Lecturer in Cybersecurity at King’s College London, presented the risks of data privacy in women’s health data, which sits at the intersection of reproductive rights, insurance and, increasingly, legal risk. She presented research with women in the United States seeking sexual and reproductive health information from AI chatbots, some of them in states that restrict access to abortion. Participants valued the privacy, availability and non-judgemental tone of these tools, with some awareness of risks. Many wrongly believed that deleting a chat history erased what a model had learned. The uncomfortable


November 2026 I www.clinicalservicesjournal.com 47


Suriyo - stock.adobe.com


t


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44  |  Page 45  |  Page 46  |  Page 47  |  Page 48  |  Page 49  |  Page 50  |  Page 51  |  Page 52  |  Page 53  |  Page 54  |  Page 55  |  Page 56  |  Page 57  |  Page 58  |  Page 59  |  Page 60  |  Page 61  |  Page 62  |  Page 63  |  Page 64  |  Page 65  |  Page 66  |  Page 67  |  Page 68  |  Page 69  |  Page 70  |  Page 71