Connect with us

Diagnosis

AI-powered mammograms: a new window into heart health

Published

on

Mammograms used in combination with AI may reveal much more than cancer,  but can also be used to assess the amount of calcium build up in the arteries within breast tissue – an indicator of cardiovascular health, a new study shows.

While breast artery calcifications can be seen on mammogram images, radiologists do not typically quantify or report this information to women or their clinicians.

This new study, which used an AI image analysis technique not previously used on mammograms, demonstrates how AI can help fill this gap by automatically analysing breast arterial calcification and translating the results into a cardiovascular risk score.

“We see an opportunity for women to get screened for cancer and also additionally get a cardiovascular screen from their mammograms,” said Theo Dapamede, postdoctoral fellow at Emory University in Atlanta and the study’s lead author.

 

“Our study showed that breast arterial calcification is a good predictor for cardiovascular disease, especially in patients younger than age 60. If we are able to screen and identify these patients early, we can refer them to a cardiologist for further risk assessment.”

Heart disease is the leading cause of death in the United States but remains underdiagnosed in women and there is also lagging awareness. Researchers said the use of AI-enabled mammogram screening tools could help identify more women with early signs of cardiovascular disease by taking better advantage of screening tests that many women routinely receive.

A build up of calcium in blood vessels is a sign of cardiovascular damage associated with early-stage heart disease or aging. Previous studies have shown that women with calcium build up in the arteries face a 51 per cent higher risk of heart disease and stroke.

To develop the screening tool used for this study, researchers trained a deep-learning AI model to segment calcified vessels in mammogram images, which appear as bright pixels on X-rays, and calculate the future risk of cardiovascular events based on data obtained from the electronic health record data.

The segmentation approach is what separates this model from previous AI models developed for analysing breast artery calcifications. Researchers said the model is also strengthened by its use of a large dataset for training and testing, which included images and health records from over 56,000 patients who had a mammogram at Emory Healthcare between 2013 and 2020 and had at least five years of follow-up electronic health records data.

“Advances in deep learning and AI have made it much more feasible to extract and use more information from images to inform opportunistic screening,” Dapamede said.

Overall findings showed the new model performed well at characterizing patients’ cardiovascular risk as low, moderate or severe based on mammogram images.

After calculating the risk of dying from any cause or suffering an acute heart attack, stroke or heart failure at two years and five years, the model showed that the rate of these serious cardiovascular events increased with breast arterial calcification level in two of the three age categories assessed – women younger than age 60 and age 60 to 80, but not in those over age 80.

This makes the tool particularly well suited for providing early warning of heart disease risk in younger women, who can benefit more from early interventions, researchers said.

The results also showed that women with the highest level of breast arterial calcification (above 40 mm2) had a significantly lower five-year rate of event-free survival than those with the lowest level (below 10 mm2).

For example, 86.4 per cent of those with the highest breast arterial calcification survived for five years compared with 95.3 per cent of those with the lowest level of calcification. This translates to approximately 2.8 times the risk of death within five years in patients with severe breast arterial calcification compared to those with little to no breast arterial calcification.

The AI model was developed as a collaboration between Emory Healthcare and Mayo Clinic and is not currently available for use.

If it passes external validation and gains approval from the U.S. Food and Drug Administration, researchers said the tool could be made commercially available for other health care systems to incorporate into routine mammogram processing and follow-up care.

The researchers also plan to explore how similar AI models could be used for assessing biomarkers for other conditions, such as peripheral artery disease and kidney disease, that might be extracted from mammograms.

Diagnosis

Lymph nodes could reveal who’s most at risk of breast cancer spreading

Published

on

Changes in lymph nodes may help show which breast cancer patients face higher or lower risk of the disease spreading, researchers have found.

The findings could support more tailored care, new treatments and help more people avoid unnecessary treatment.

Dr Simon Vincent is chief scientific officer at Breast Cancer Now, which funded the research:

He said: “These findings suggest that changes to the structure of the lymph nodes are more than just a consequence of the cancer. They can also play an active role in helping breast cancer progress.

“With one person tragically dying from breast cancer every 45 minutes in the UK, we urgently need research like this so that we can better understand who is most at risk of their cancer progressing and becoming incurable. Only then we can find ways to stop it.

“With a better understanding of how lymph nodes change as breast cancer spreads, we could find new targets for future treatments for types of breast cancer that are harder to treat.”

Lymph nodes, a key part of the immune system, help the body fight infections and cancer. In breast cancer, the lymph nodes in the armpit are often the first place the disease spreads to.

At the moment, everyone with invasive breast cancer has to undergo surgery to remove lymph nodes so doctors can check for cancer cells.

Invasive breast cancer means cancer that has spread beyond where it first developed in the breast into nearby tissue.

While this is effective, it can lead to long-term side effects such as swelling of the arm, known as lymphoedema, and may be unnecessary for some patients, particularly those with early-stage disease or those whose cancer responds well to treatment.

The study analysed 331 lymph node samples from people with different types of breast cancer and compared them with healthy lymph nodes from people free from the disease.

It found that breast cancer could change the structure of a network that supports the lymph nodes.

Crucially, some of these changes could occur before doctors were able to spot any cancer cells in the network.

Some changes were linked to a better chance of survival, while others were associated with a poorer prognosis.

Dr Amy Llewellyn and Dr Kalnisha Naidoo from King’s College London, together with professor Sophie Acton at University College London, compared the 331 samples with healthy lymph nodes in people free from the disease.

They looked at fibroblastic reticular cells, known as FRCs, a group of cells in lymph nodes that provide their structure, control fluid flow and activate different immune cells.

The study showed that the structure of this FRC network could change before the cancer had spread and differed depending on the type of breast cancer, any spread and whether someone had received chemotherapy.

Chemotherapy uses medicines to kill cancer cells or slow their growth.

The researchers said the findings could help doctors better understand who is most at risk of breast cancer spreading.

Dr Llewellyn said the first large-scale analysis of FRC in human lymph node tissue from breast cancer patients was addressing the “urgent need” for a better understanding of the area’s biology.

Continue Reading

Fertility

AMH testing: the most misunderstood number in fertility – what it can and can’t tell you

Published

on

Article produced in association with Spital Clinic

AMH has become one of the most-requested blood tests in private women’s health. The number it gives back is useful, but only when it is read in context.

AMH testing in the UK has gone mainstream over the past few years. Home-testing kits sell it as a snapshot of “your fertility”.

Private clinics include it in screening packages. On social media, individual AMH results are now routinely treated as a verdict on whether a woman will be able to have children.

That reading isn’t accurate. Anti-Müllerian Hormone (AMH) does carry useful information, but only inside a wider clinical picture.

Looked at on its own, it produces a lot of unnecessary anxiety, and often hides the questions that matter more.

What AMH measures

AMH is a hormone produced by the small follicles in the ovaries, the ones that haven’t yet been recruited for ovulation. Because these follicles are relatively stable across the menstrual cycle, the test can be done on any day, without needing to be timed to a period.

A higher AMH level tends to indicate a larger pool of these follicles. A lower level suggests the pool is smaller. That, broadly, is what the result shows.

The HFEA, the UK’s independent regulator of fertility treatment, describes AMH as an indicator of ovarian reserve, while making clear that fertility test results of this kind “are not guaranteed” as a predictor of fertility outcomes.

Put simply: AMH is a count of what is there. It says nothing about how well the body will use it, and it cannot predict if or when conception will happen.

Where AMH fits in a modern fertility assessment

In current UK private practice, AMH is rarely tested in isolation. A meaningful fertility assessment will pair it with a fuller hormone profile (FSH, LH, oestradiol, prolactin and thyroid function), along with markers such as Day 21 progesterone, vitamin D and rubella immunity where relevant.

This is the structure used in a trying-to-conceive screening, and there is a reason for it: each of these tests answers a different question that AMH on its own cannot.

It is this combination, not the AMH number on its own, that gives a clinician enough information to say anything meaningful about an individual’s reproductive picture.

Misconception 1: “A low AMH means natural pregnancy isn’t possible”

This is the misconception that causes the most distress, and it is consistently wrong.

Several large prospective studies of women in their 30s and 40s trying to conceive naturally have found that women whose biomarkers, including AMH, pointed to a diminished ovarian reserve were no less likely to conceive within twelve cycles than women with reassuring results.

That is why neither UK regulators nor national guidance treat AMH as a test that can predict natural fertility in women who have no known infertility issue.

The reason is simple. Natural conception only requires one good egg, released in a normal cycle, in the right window.

AMH doesn’t measure egg quality, and it doesn’t reveal whether ovulation is happening. A woman with low AMH may still ovulate every month with high-quality eggs.

A woman with high AMH (often the pattern seen in polycystic ovary syndrome) may not be ovulating regularly at all.

The NHS emphasises that age is the strongest single predictor of natural fertility. A 35-year-old with a low AMH and regular cycles is, on average, more likely to conceive naturally than a 40-year-old with a normal AMH and irregular ones.

If AMH comes back low for someone who is trying to conceive, the more useful question isn’t whether pregnancy is still possible (the answer is almost always yes), but whether there is reason to investigate the wider picture now rather than waiting twelve months.

Misconception 2: “A normal AMH means everything is fine”

The opposite assumption is just as risky.

AMH tells you about egg quantity. It does not tell you about:

  • Egg quality, which is closely tied to age
  • Whether ovulation is happening regularly
  • Whether the fallopian tubes are open
  • Whether there are structural issues such as fibroids, polyps, ovarian cysts or endometriosis
  • Sperm parameters in a male partner
  • Whether implantation will succeed

A reassuringly normal AMH at 38 still sits alongside age-related changes in egg quality. A slightly lower-than-average AMH at 28 may carry no real-world implications at all.

That is why no UK clinical body recommends AMH as a routine screening test for healthy women who have no fertility concerns. NICE’s fertility guideline, NG73, treats AMH as one component of a broader investigation, not as a verdict in itself.

Imaging is the natural counterpart to the blood test. A transvaginal pelvic ultrasound directly visualises the small follicles that produce AMH, the antral follicle count. It also picks up structural findings a blood test will never reveal, including ovarian cysts, fibroids, polycystic ovarian morphology, and abnormalities in the uterine cavity. A full ovarian reserve assessment normally includes both.

Where the AMH number actually matters

There are three settings in which AMH carries real, decision-relevant information.

Before IVF or egg freezing. AMH is one of the better predictors of how the ovaries are likely to respond to stimulation medication.

A higher AMH usually predicts more eggs collected per cycle, and a very low AMH may shape decisions about protocol or whether to bank cycles before treatment.

During a fertility investigation. If a couple has been trying for twelve months, or six months if the woman is over 35, AMH becomes part of a wider assessment that should also include ovarian ultrasound, a fuller hormone profile, semen analysis and an assessment of tubal patency.

As context for women planning ahead. Women who want to understand their reproductive options before they are ready to conceive (for example, ahead of a decision about egg freezing) can find AMH informative, provided it is interpreted alongside age, antral follicle count, and other markers, by a clinician who can place the number in context.

Reading the number properly

For anyone who has had an AMH test, three things make the result more useful:

  1. Pair it with age. A “normal” AMH at 25 means something very different from the same number at 38. Age is doing more work in the equation than the AMH value itself.
  2. Pair it with imaging. Ultrasound shows what is actually in the ovaries today, rather than relying on a single biochemical marker.
  3. Read it with a clinician. A number on a screen, with no context, no follow-up and no plan, is the worst way to use a test that, properly interpreted, can be very informative.

AMH is a useful tool. It just isn’t the headline it has often been turned into.

Disclaimer

This article is produced for informational purposes only and does not constitute medical advice, diagnosis or treatment. Clinical guidance referenced reflects published HFEA, NHS and NICE information available as at May 2026. Individual circumstances vary; readers are advised to consult a qualified healthcare professional before acting on any information in this article. This piece was produced in association with Spital Clinic, which provided background clinical information for editorial purposes. Hyperlinks to external sources are included for reference only and do not represent an endorsement of any product, service or organisation.

Continue Reading

Wellness

Being female not a universal stroke risk factor for patients with AF, study finds

Published

on

Female sex may not raise stroke risk across all atrial fibrillation (AF) patients, with higher risk mainly seen in women aged 75 and older, a study suggests.

Researchers said stroke prevention for women with the condition should be more personalised, especially for patients under 75.

Dr Amitabh C Pandey, director of cardiovascular translational research at Tulane University School of Medicine, said: “For years, female sex has been included as a risk factor along with other factors such as high blood pressure and diabetes, meaning women were more likely to be prescribed anticoagulants.

“Our study shows younger women may not have as much added stroke risk as previously thought, while older women, particularly those over 75, appear to have a higher risk that deserves close attention.”

The new Tulane University study challenges a long-standing assumption in heart care that being female automatically increases stroke risk for patients with atrial fibrillation.

Atrial fibrillation, often called AF, is a common heart rhythm disorder that causes the heart to beat irregularly.

It is associated with a higher risk of stroke and is often treated with anticoagulants, also known as blood thinners.

The study found that stroke risk did not increase equally across all female patients with AF.

Instead, researchers said being female may act more as a risk modifier, with increased stroke risk seen primarily among women aged 75 and older or those with a greater burden of other health conditions.

Clinicians often use a scoring system to decide whether people with AF should be prescribed blood thinners.

The system gives points for factors including age, heart failure, diabetes, previous stroke, vascular disease and high blood pressure.

Women also receive one point for sex alone.

Researchers said this can mean women with AF become eligible for blood thinners earlier or more often than men with otherwise similar risk profiles.

While blood thinners can help prevent clot-related strokes, they can also increase the risk of bruising, prolonged bleeding, gastrointestinal bleeding and other serious complications.

The researchers analysed approximately 950,000 patients with AF using TriNetX, a large anonymised electronic health record database.

They compared stroke outcomes between male and female patients across three age groups: younger than 65, 65 to 74, and 75 and older.

Male and female patients were matched based on age, other health problems and whether they had been prescribed anticoagulation medicine.

Among patients younger than 75, the study found no significant difference in one-year stroke risk between men and women.

However, among patients aged 75 and older, women had a modest but statistically significant increase in stroke risk compared with men.

In patients aged 75 and older with no additional risk factors beyond age, women had about one additional stroke per 629 patients compared with their male counterparts.

The findings support growing interest in a newer AF risk score, known as CHA2DS2-VA, which removes sex as a standalone risk factor.

However, researchers said more studies are needed and medical guidance remains inconsistent.

Han Feng, assistant professor at Tulane University School of Medicine, said: “This general approach came from women being underrepresented in AFib trials and studies comprising only about one-third of study populations.

“Our study shows not all women with AFib have the same risk profile, and these decisions should be individualised.

Pandey said: “These findings highlight the need for modern tools and approaches that can personalise risk profiles to individuals.

“The goal is not to undertreat patients who need stroke prevention, but to better identify who is most likely to benefit from anticoagulation and who may be exposed to unnecessary risk.”

Continue Reading

Trending

Copyright © 2025 Aspect Health Media Ltd. All Rights Reserved.