News
AI system could cut diagnosis time for women with endometriosis
The technology combines the diagnostic capabilities of pelvic scans and MRI to identify endometriosis lesions
A new artificial intelligence system could improve the quality of life of millions of women suffering from endometriosis.
The IMAGENDO system, developed by the University of Adelaide in South Australia, in partnership with researchers from the University of Surrey, uses machine learning to analyse data from pelvic scans and magnetic resonance imaging (MRI) to identify endometriosis lesions.
One in ten women lives with endometriosis, a chronic condition where endometrial-like tissue grows outside the uterus.
The World Health Organization (WHO) estimates that “at least” six and a half million women in the US alone have the condition, a figure that rises to as high as 190 million globally.
In the UK, it takes on average eight years from the onset of symptoms to get a diagnosis. This lengthy process can lead to anxiety, depression and fatigue, often requiring patients to consult with multiple health professionals.
The current recommendation for obtaining a clear diagnosis is laparoscopic surgery, a procedure that allows surgeons to examine the organs inside the abdomen and detect endometrial deposits.
The IMAGENDO study aims to reduce the need for surgery and cut the time it takes to receive a diagnosis.
Professor Gustavo Carneiro, professor of AI and machine learning at the University of Surrey and one of the chief investigators of IMAGENDO, said: “IMAGENDO is introducing innovative AI capabilities to provide fast, non-invasive endometriosis diagnosis by combining MRI and ultrasound technology.
“While the legitimate concerns about the use of AI have dominated the headlines, here is an example of how this technology can improve the lives of millions of people who suffer from endometriosis and severe pelvic pain.”
Development of IMAGENDO is being led by the Robinson Research Institute, University of Adelaide, Australia. The project has recently been shortlisted for the prestigious ANSTO Eureka Prize for Innovative Use of Technology.
The Eureka Prizes are awarded by the Australian Museum every year to recognise individuals and organisations who have contributed to science in Australia.
The FDA will remove the menopause drug warning from hormone therapies, citing updated evidence on stroke and heart risks.
US health officials said Monday they will drop the boxed warning — the strongest safety alert on a drug label — from more than 20 pills, patches and creams with hormones such as oestrogen and progestin, used to ease hot flushes and night sweats.
The 22-year-old warning told doctors that hormone therapy raises the risk of blood clots, heart problems and other issues, based on an influential study published more than 20 years ago.
FDA commissioner Marty Makary called the current label outdated and unnecessary. Officials pointed to studies suggesting hormone therapy carries few risks when started before age 60 and within 10 years of symptoms beginning.
health secretary Robert F. Kennedy Jr. said: “We’re challenging outdated thinking and recommitting to evidence-based medicine that empowers rather than restricts.”
Medical guidelines generally advise limited-duration use in younger women going through the menopause who do not have complicating risks, such as breast cancer. The FDA’s updated prescribing information largely aligns with that approach.
Makary and some other doctors have argued that benefits may extend beyond symptom relief. Before becoming FDA commissioner, Makary devoted a chapter of his latest book to what he described as the overall benefits of hormone therapy and criticised doctors unwilling to prescribe it.
On Monday he repeated that view, citing figures suggesting hormone therapy reduces heart disease, Alzheimer’s and other age-related conditions. Makary told reporters: “With few exceptions, there may be no other medication in the modern era that can improve the health outcomes of women at a population level more than hormone replacement therapy.”
The scale of those benefits remains under study. Dr JoAnn Manson of Harvard Medical School said the evidence for overall health benefits is not “as conclusive or definitive” as Makary suggested.
Still, she said removing the warning could help doctors and patients make more personalised decisions. Manson said: “The black box is really one size fits all. It scares everyone away. Without the black box warning there may be more focus on the actual findings, how they differ by age and underlying health factors.”
In the 1990s, more than one in four US women took oestrogen alone or with progestin, amid assumptions it would cut rates of heart disease, dementia and other problems, as well as treat symptoms.
But a landmark study of more than 26,000 women challenged that, linking two hormone pill types to higher rates of stroke, blood clots, breast cancer and other serious risks. After the 2002 findings were published, prescriptions fell across age groups.
Makary said: “That study was misrepresented and created a fear machine that lingers to this day.”
A new analysis of the 2002 data, published in September, found women in their 50s on oestrogen-based drugs had no increased risk of heart problems, while women in their 70s did; the data for women in their 60s was unclear.
Since the early 2000s, newer forms have arrived, including vaginal creams and tablets that deliver lower doses than pills and patches.
The original warning language will still be available to prescribers but placed lower on the label. The drugs will keep a boxed warning that women who have not had a hysterectomy (surgical removal of the uterus) should take a combination of oestrogen-progestin due to the risk of cancer in the uterine lining.
Rather than convening one of the FDA’s standing advisory committees on women’s health or drug safety, Makary earlier this year invited a dozen doctors and researchers who overwhelmingly supported the health benefits of hormone-replacement drugs. Many of the panellists at the July meeting consult for drugmakers or prescribe the medicines in private practice. Two of the experts also spoke at Monday’s FDA news conference.
Asked Monday why the FDA did not convene a formal advisory panel, Makary said such meetings are “bureaucratic, long, often conflicted and very expensive.”
Diana Zuckerman of the non-profit National Centre for Health Research accused Makary of undermining the FDA’s credibility by announcing the change “rather than having scientists scrutinise the research at an FDA scientific meeting.”
A London executive is suing a fertility clinic, alleging its IVF treatment led to her suffering a stroke.
Navkiran Dhillon-Byrne, 51, began private IVF treatment at the Assisted Reproduction and Gynaecology Centre (ARGC) in Wimpole Street, London, in April 2018.
Ten days after her treatment ended, on 28 April 2018, she suffered a stroke, which her lawyers say has left her with ongoing vision problems.
Ms Dhillon-Byrne is now suing the clinic and its head, Mohamed Taranissi, for negligence and breach of duty, saying medics failed to give her sufficient warnings about stroke risks linked to IVIg immunotherapy (intravenous immunoglobulin) – a one-off add-on treatment designed to moderate the body’s immune responses during pregnancy.
The clinic and Dr Taranissi deny liability, saying Ms Dhillon-Byrne was fully informed of the risks.
They also dispute that IVIg caused her stroke.
Central London County Court heard that Ms Dhillon-Byrne, chief marketing officer at the City of London base of an international software company, turned to private treatment after the NHS was unable to fund her IVF in 2014.
She had an unsuccessful attempt at another London clinic before choosing ARGC. She told the court she had been trying to have a child since 2014.
She said she selected ARGC after a friend recommended it, praising what they described as high success rates.
The clinic’s website describes its approach as “IVF boot camp” and promotes “in-depth investigations, daily monitoring and real-time treatment adjustments.”
Ms Dhillon-Byrne says she was not warned of the “specific” risks of thrombosis – blood clotting that can lead to stroke – in relation to the IVIg therapy.
She also says the clinic overstated her chances of success and failed to secure her “informed consent” before treatment began.
She argues that, had she been given a clear picture of her chance of a successful pregnancy, she would not have consented to IVF and the supplemental IVIg therapy.
Denying Ms Dhillon-Byrne’s claims, the clinic’s KC, Clodagh Bradley, told the court that the success rate advice given was “accurate and in accordance with the ARGC data.”
She added that Ms Dhillon-Byrne had been informed that the immune treatment was new and “still controversial.”
Lawyers said outside court that, if successful, Ms Dhillon-Byrne’s claim is likely to be worth “millions” due to the impact of the stroke on her high-flying career.
The trial continues.
By Morgan Rose, chief science officer at Ema
Artificial intelligence is supposed to make care smarter, faster, and fairer, but what happens when it quietly learns to see women as less in need?
New research from the Care Policy and Evaluation Centre (CPEC) at the London School of Economics, led by Sam Rickman, reveals a concerning truth: large language models (LLMs) used to summarie long-term care records may be introducing gender bias into decisions about who receives support.
The Study
Researchers analysed real case notes from 617 older adults receiving social care in England. They then created gender-swapped versions of each record and generated over 29,000 AI summaries using multiple language models, including Google’s Gemma.’
The goal was simple: would AI treat men’s and women’s needs the same way?
It didn’t.
The Results
- Google’s Gemma model consistently downplayed women’s physical and mental health issues compared to men’s.
- Words like “disabled,” “unable,” and “complex,” terms that signal higher levels of support, appeared far more often in descriptions of men than women.
- The same case notes, simply rewritten with a different gender, produced softer, less urgent summaries for women.
In other words, when the algorithm rewrote her story, her needs shrank.
The Cost of Softer Language
Language isn’t neutral. In healthcare, it’s the difference between monitor and act.
Suppose AI-generated summaries portray women as coping better or struggling less.
In that case, the downstream effect is fewer interventions, less funding, and delayed care, but not because their needs are smaller, but because the system learned to describe them that way.
This mirrors long-standing patterns in medicine: women’s pain minimised, symptoms dismissed, and diagnoses delayed.
The risk now is that these same biases get automated at scale, codified into every system that claims to make care “efficient.”
Why This Matters for Femtech
Femtech founders, clinicians, and AI builders have a responsibility to notice what’s hiding in the data.
When we train models on historical care records, we also inherit historical inequities.
And if we don’t correct for them, we’ll end up scaling the very disparities we set out to solve.
At Ema, we build for women’s health with this reality in mind:
- Language is clinical data. Every word shapes care pathways.
- Bias is not neutralised by scale. It’s magnified by it.
- Ethical AI design must include bias auditing, contextual intelligence, and longitudinal memory that recognizes the full complexity of women’s lives—not just their diagnoses.
The Path Forward
Fixing this isn’t about scrapping AI.
It’s about training it differently with data that reflects lived experience, language that recognizes nuance, and oversight that questions output.
Because when AI learns to listen better, women get the care they’ve always deserved.
Source:
-
News3 weeks agoDozens of women report suffering painful burns after using Always sanitary towels
-
News4 weeks agoWomen’s health innovations recognised in TIME’s Best Inventions 2025
-
Events3 weeks agoCutting through the noise in femtech – key takeaways from Women’s Health Week 2025
-
Mental health4 weeks agoMenstrual cycle affects women’s reaction time, study finds
-
News2 weeks agoAI embryo selection tool wins European approval
-
News3 weeks agoScientists develop breakthrough approach to detecting endometriosis in menstrual blood
-
News2 weeks agoTestosterone patch shows promise for menopausal women
-
Features2 weeks agoFrom SEO to GEO: How women’s health brands can get found in the age of AI