AI may help detect heart disease in women from routine mammograms, according to research involving almost 30,000 women.

Researchers found a machine-learning model could distinguish women with coronary heart disease, high blood pressure or a previous stroke using mammogram images.

The findings suggest breast cancer screening could potentially also flag cardiovascular problems without requiring an additional imaging examination.

Dr Viana Copeland, from Tel Aviv University, presented the findings at the European Society of Cardiology’s annual congress in Munich.

The researcher said: “Despite being the leading cause of death in women worldwide, CVD [cardiovascular disease] is consistently underdiagnosed and undertreated.

“A common finding in our medical centre, and around the world, is that when women do seek medical help, their CVD is already advanced.

“On the other hand, many women do attend routine breast cancer screening, even when they haven’t sought care for cardiovascular symptoms.

Researchers in Israel analysed 97,364 mammogram scans from 29,921 women with an average age of 54 and cross-referenced the images with their medical records.

Among the women, 16 per cent had high blood pressure, 2.5 per cent had coronary heart disease and 2.5 per cent had experienced a stroke.

A machine-learning model was trained to identify women with these conditions.

Using mammograms alone, the model could distinguish women who had experienced a stroke from those who had not 86 per cent of the time.

For high blood pressure, the figure was 79 per cent, while for coronary heart disease it was 78 per cent.

The results were consistent regardless of age or whether a woman also had cancer.

Copeland said analysing existing mammograms for information about cardiovascular health “could potentially offer a scalable approach without requiring an additional imaging examination”.

“Mammography also reaches many women in midlife, an important period for recognising and addressing cardiovascular risk.”

Researchers are working to improve the model’s accuracy, reduce false results and increase the number of heart conditions it can identify.

Elena Arbelo, an expert member of the European Society of Cardiology communication committee, described the findings as “compelling”.

“A mammogram may one day do more than look for breast cancer – it may also offer a window on to cardiovascular health. That matters because CVD in women is still too often recognised late.”

She added: “The challenge now is to establish accuracy and reliability – to move from experimentation to clinical implementation.”

Prepared for Femtech World by Dr Emilė Radytė, neuroscientist and co-founder and CEO of Samphire Neuroscience

The short answer

Premenstrual dysphoric disorder (PMDD) does not usually result from abnormal hormone levels.

Research suggests that the brain can respond differently to expected changes in estrogen, progesterone, and the progesterone metabolite allopregnanolone.

This helps explain why blood tests can look typical while a person’s experiences remain severe. It also gives researchers a clear reason to study nervous-system treatments alongside selective serotonin reuptake inhibitors (SSRIs), hormonal treatment, and psychological care.

Why can expected hormone changes cause severe PMDD experiences?

Hormones act as signals. They interact with receptors throughout the brain and influence networks involved in mood, stress, sleep, and emotional regulation.

Two people can have similar hormonal patterns and experience those signals in different ways.

Hantsoo and Epperson (2020) reviewed evidence that PMDD involves an altered response to changing levels of allopregnanolone, which modulates gamma-aminobutyric acid type A (GABA-A) receptors. GABA helps regulate neural activity and the stress response.

In PMDD, the issue may lie in the brain’s adaptation to allopregnanolone fluctuations across the menstrual cycle.

Experimental research supports this sensitivity model. Suppressing ovarian hormone fluctuations can reduce PMDD experiences in susceptible participants, while reintroducing physiologic concentrations can bring them back.

Researchers therefore describe PMDD as a disorder of sensitivity to hormonal change, while recognizing that no single pathway explains every case.

Do normal hormone test results rule out PMDD?

No. A blood test shows whether a hormone concentration falls within an expected range at one point in time.

It cannot show how a person’s brain responds to that signal across the cycle.

Clinicians diagnose PMDD by its timing and impact, using prospective daily ratings across menstrual cycles.

The American College of Obstetricians and Gynecologists (ACOG) recognises PMDD as part of a spectrum of premenstrual disorders and recommends an individualised, multimodal approach.

Which treatments have evidence for PMDD?

ACOG’s 2023 clinical practice guideline includes hormonal and nonhormonal medicines, psychological counseling, exercise, nutritional approaches, patient education, and surgery for selected cases.

SSRIs can work faster in PMDD than they often do in major depression. Hormonal approaches can suppress ovulation or stabilize fluctuations for some patients.

No treatment works for every person. Some patients do not improve, cannot tolerate side effects, have contraindications, or prefer another route.

When that happens, clinicians and researchers need to ask which part of the biological pathway still drives the condition.

Could brain stimulation treat PMDD?

Noninvasive brain stimulation offers a plausible research direction because it can influence neural networks involved in mood regulation.

Evidence from depression cannot establish that it works for PMDD.

Researchers need PMDD-specific randomised trials that measure experiences across the cycle and report safety, adherence, and clinically meaningful outcomes.

The distinction matters. A coherent mechanism creates a hypothesis. Only indication-specific clinical evidence can establish efficacy.

Key takeaways

• PMDD can occur with hormone levels that fall within expected ranges.
• Research points to altered brain sensitivity to hormonal change, including allopregnanolone fluctuations.
• SSRIs and hormonal approaches remain evidence-based options, often as part of multimodal care.
• Brain stimulation is a research target for PMDD, not a conclusion that can be borrowed from depression studies.

Learn more at https://www.samphireneuro.com/en-us/pmdd

Sources:

Hantsoo and Epperson (2020), Allopregnanolone in premenstrual dysphoric disorder.

American College of Obstetricians and Gynecologists (2023), Management of premenstrual disorders.

Thousands of UK women develop undiagnosed PTSD after childbirth each year, with at least 15,000 cases going undetected, researchers say.

The true number could be double that or more, according to an evidence review of childbirth-related post-traumatic stress disorder (PTSD).

PTSD can involve symptoms including nightmares, flashbacks, anxiety and persistent negative thoughts. Research estimates suggest between 5 and 5.9 per cent of women giving birth develop the condition.

Doctors at the University of East Anglia’s medical school reviewed existing data on births, PTSD prevalence and six-week postnatal GP appointments to estimate how many cases are going undiagnosed.

They said many GPs mistake childbirth-related PTSD for postnatal depression, potentially resulting in women receiving treatment that is not appropriate for PTSD.

Research has estimated that fewer than half of women with postnatal PTSD symptoms are diagnosed and receive NHS care.

Lead author Dr Megan Foreman, who is also a GP, said: “The Office for National Statistics figure for the 2025 live birthrate in England and Wales, not including Scotland and Northern Ireland, was 585,396.

“This figure does not include stillbirths and miscarriages, which are significant risk factors for childbirth-related PTSD.

“Therefore, at 5 per cent of the 2025 ONS birthrate for England and Wales (29,269), combined with the evidence from Moran et al that less than 50 per cent of women with PTSD symptoms postnatally are referred for specialist perinatal mental health support, a UK figure greater than 15,000 women, but potentially in the tens of thousands, would be justifiable based on the available evidence.”

The researchers said cases are being missed during the NHS six-week postnatal check, which assesses the health of both the mother and baby.

There is no approved framework for assessing a woman’s risk of childbirth-related PTSD during these appointments, they said.

Assessing a newborn’s health can also make it harder to focus on the mother’s mental health, particularly if she attends the appointment alone with her baby.

The researchers also noted that some women may not feel able to discuss a traumatic birth soon afterwards because doing so could retrigger the experience.

The review cited UK research in which half of GPs recognised trauma-related features in case examples of childbirth-related PTSD, but postnatal depression remained their most common diagnosis.

The authors said misdiagnosis could be detrimental because women may be prescribed antidepressants, which are not as effective for treating PTSD as psychological therapy.

Treating depression alone may also fail to improve coexisting childbirth-related PTSD.

Identifying the condition is particularly important because both PTSD and postnatal depression are associated with an increased risk of suicide, the most common cause of death among women in the year after giving birth, the authors said.

The review also said untreated childbirth-related PTSD can affect women and their families, contribute to further healthcare needs, lead to avoidance of doctors and hospitals and influence decisions around future pregnancies.

Angela McConville, chief executive of parenting charity NCT, said: “The possibility that so many women could be living with undiagnosed PTSD after birth is deeply concerning.

“PTSD after birth is a serious and often overlooked condition that can have a profound impact on women and new mothers, as well as those around them.

“No one should have to reach crisis point before they are listened to and able to access support.

“These findings are a powerful reminder that birth trauma does not end when care in hospital ends.

“When trauma goes unrecognised or unsupported, the effects can be felt across relationships, family life and wellbeing for months or even years.”