Diagnosis
AI outperforms breast density for breast cancer risk
An artificial intelligence model predicts five-year breast cancer risk more accurately than traditional breast density assessment, new research shows.
The image-only AI model, called Clairity Breast, showed that women in its high-risk group had more than a fourfold higher cancer incidence than those in the average-risk group (5.9 per cent vs 1.3 per cent).
Breast density, which refers to the amount of fibrous and glandular tissue compared to fatty tissue in the breast, has traditionally been used as one indicator of cancer risk. Dense breast tissue can both mask tumours and slightly increase cancer risk.
Researchers from Harvard Medical School and University Hospital RWTH Aachen in Germany tested the FDA-authorised AI model on 245,232 screening mammograms from US and European sites taken between 2011 and 2017.
The AI was trained on 421,499 mammograms from 27 facilities across Europe, South America and the US, learning to identify subtle tissue patterns that predict cancer development within five years. It uses a deep convolutional neural network (a pattern-recognition algorithm) to generate risk probabilities.
Traditional density assessment showed minimal difference in outcomes: 3.2 per cent for dense versus 2.7 per cent for non-dense breasts.
“Over two million women are diagnosed with breast cancer annually, and for most, it comes as a complete shock,” said Dr Constance D. Lehman, professor of radiology at Harvard Medical School. “Only 5 to 10 per cent of breast cancer cases are considered hereditary, and breast density alone is a very weak predictor of risk.”
The AI categorised risk using National Comprehensive Cancer Network thresholds: average (less than 1.7 per cent), intermediate (1.7-3.0 per cent) and high (greater than 3.0 per cent) five-year risk.
“The model is able to detect changes in the breast tissue that the human eye can’t see,” Dr Lehman explained. “This is a job that radiologists just can’t perform. It’s a separate task from detection and diagnosis, and it will open a whole new field of medicine, leveraging the power of AI and untapped information in the image.”
The findings have particular significance for younger women. While the American Cancer Society recommends optional annual screening from age 40 for average-risk women, those under 40 represent the fastest-growing group diagnosed with breast cancer and advanced disease.
“An AI image-based risk score can help us identify high-risk women more accurately than traditional methods and determine who may need screening at an earlier age,” Dr Lehman said. “We already screen some women in their 30s when they are clearly at high risk based on family history or genetics. In the future, a baseline mammogram at 30 could allow women with a high image-based risk score to join that earlier, more effective screening pathway.”
Dr Christiane Kuhl, director of the Department of Diagnostic and Interventional Radiology at University Hospital RWTH Aachen, who presented the findings, emphasised the clinical implications.
“The results of this large-scale analysis demonstrate that AI risk models provide far stronger and more precise risk stratification for five-year cancer prediction than breast density alone,” she said. “Our findings support the use of image-only AI as a complement to traditional markers supporting a more personalised approach to screening.”
Currently, 32 US states have breast density legislation requiring healthcare providers to inform women of their density status after screening mammograms. The researchers suggest this information could be enhanced with AI risk scores.
“We’d like to see women given information on their breast density and their AI image-based risk score,” Dr Lehman said. “We can do better than just looking at a mammogram and saying, ‘It is dense or not dense’ to inform women of their risk.”
The technology represents what its developers describe as a shift in breast cancer screening from population-based to personalised risk assessment, potentially enabling earlier intervention for high-risk women while reducing unnecessary procedures for those at lower risk.
Menopause is often absent from women’s electronic health records, a study of nearly 396,000 women has found.
Researchers found menopause appeared almost seven times more often in participant surveys than in electronic health records (EHRs).
The findings suggest important reproductive health information, including age at menopause, may often be missing from health records used for research.
Audrey Hendricks, associate professor of bioinformatics at CU Anschutz and the study’s principal investigator, said: “Ultimately, we cannot study what we do not measure. We cannot treat what we do not know.
“Menopause has enormous implications for women’s health, but if we don’t consistently capture when menopause occurs and other important reproductive health information, we limit our ability to understand how this transition affects disease risk and health outcomes.”
Researchers at the University of Colorado Anschutz analysed data from women taking part in the National Institutes of Health’s All of Us Research Program.
They compared menopause information reported by participants in surveys with menopause diagnoses recorded in their electronic health records.
Around 193,000 menopause observations were identified in survey data, compared with approximately 28,000 diagnoses in EHR data.
Menopause was documented in electronic health records for only about 7 per cent of women in the dataset.
Nearly all participants with a menopause diagnosis recorded in their EHR also reported menopause in survey data. However, substantially fewer women had menopause documented in their health records.
Other important information was also frequently unavailable, including age at menopause, which researchers may use when examining links between menopause and chronic disease risk.
Menopause is a physiological transition that can affect cardiometabolic health and many other aspects of women’s health.
Researchers said relatively little is known about how factors including the timing and type of menopause influence health outcomes across diverse populations.
Large-scale programmes such as All of Us combine participant surveys, electronic health records and genomic data, but menopause-related research depends on relevant reproductive health information being available.
Missing menopause information can make it harder to investigate how the transition relates to health and disease.
The findings may also help researchers using All of Us data define menopause-related study populations, design studies and estimate how many participants are needed.
Hendricks said: “We have an enormous opportunity to use large-scale datasets to understand women’s health across the menopause transition and to identify who may be at greater risk for disease.
“But we need to make sure that the information researchers need is actually being collected.
“We must do a better job of capturing women’s health information, including reproductive health and measures related to menopause.”
Researchers said more complete and consistent collection of menopause and reproductive health information could help future studies examine factors such as age at menopause and their relationship with disease risk and health outcomes.
The FDA has granted accelerated approval to AstraZeneca drug Etcamah for certain adults with advanced breast cancer carrying an ESR1 mutation.
Etcamah, also known as camizestrant, was approved in combination with a CDK4/6 inhibitor, either abemaciclib, palbociclib or ribociclib.
The treatment is for adults with hormone receptor-positive, HER2-negative, locally advanced or metastatic breast cancer when an estrogen receptor-1 (ESR1) mutation is detected during aromatase inhibitor and CDK4/6 inhibitor therapy using an FDA-authorised test.
ESR1 mutations are acquired resistance mutations that tumours may develop during treatment with aromatase inhibitors, a type of endocrine therapy commonly used as a front-line treatment for locally advanced or metastatic breast cancer.
Fewer than 5 per cent of patients have the mutation when HR-positive metastatic breast cancer is diagnosed, according to the FDA. After disease progression on an aromatase inhibitor, nearly 40 per cent have the mutation.
Acting FDA commissioner Kyle Diamantas said: “Women living with metastatic breast cancer face an uphill battle as their tumors continuously evolve to escape treatment.
“We owe them every weapon in our arsenal.
“Today’s approval delivers a win to these patients by granting them a targeted therapy designed specifically to overcome resistance, giving them more time before their disease progresses.”
The accelerated approval programme allows earlier approval of drugs that treat serious conditions and fill an unmet medical need based on surrogate or intermediate endpoints.
For Etcamah, approval was based on how long patients lived without their disease worsening, measured from when the resistance mutation was first detected in their blood.
The FDA said it has not yet been confirmed whether intervening when the mutation is detected, rather than waiting until disease progression is confirmed, results in a clinically meaningful benefit. Confirmatory studies are therefore required to verify and describe clinical benefit.
Angelo de Claro, director of the FDA’s Oncology Center of Excellence, said: “I commend both the FDA and the sponsor for their commitment to advancing cancer care and securing this accelerated approval.
“This marks the first FDA approval of a cancer therapy guided by the detection of a resistance mutation in circulating tumor DNA (ctDNA) before imaging tests show that the disease is progressing.
“But additional evidence is needed to confirm clinical benefit.”
Circulating tumour DNA, or ctDNA, consists of small pieces of tumour DNA released into the blood and can allow earlier molecular detection of resistance mutations.
The FDA also authorised the Guardant360 CDx assay as a companion diagnostic to identify patients with breast cancer who have ESR1 mutations for treatment with camizestrant.
Efficacy was assessed in a clinical trial comparing a switch to Etcamah plus a CDK4/6 inhibitor with continued treatment using an aromatase inhibitor plus a CDK4/6 inhibitor.
Estimated median progression-free survival was 16 months in the Etcamah group, compared with 9.2 months in the aromatase inhibitor group.
Etcamah’s prescribing information includes a boxed warning about the risk of irregular heart rhythm when taken with certain other medicines. It also includes warnings about an abnormally slow heart rate and potential harm to an unborn baby.
The FDA convened its Oncologic Drugs Advisory Committee for the application on 30 April 2026.
Four leading cardiovascular health groups have agreed new guidance for healthcare professionals assessing patients with suspected heart attacks.
Historically, some less common forms of heart attack, which evidence shows affect women far more than men, have been classified as less important, with treatment and care often worse as a result.
Experts said women had been receiving less effective treatments that did not always target the specific cause of their heart attack and could even make them more unwell.
The changes were announced in Munich on the opening day of the annual congress of the European Society of Cardiology (ESC).
Professor Bryan Williams, chief scientific and medical officer of the British Heart Foundation, said: “This is a landmark moment, a radical shift in how we define and diagnose heart attacks worldwide which will transform people’s care.
“For decades, women have missed out on accurate diagnoses and treatment.
“This focus on finding less common causes of heart attacks, which predominantly affect women, should help to change that. It could be life-changing for huge numbers of women in the UK and worldwide.”
The new guidance upgrades three types of heart attack that can be up to 10 times more common in women and are often caused by childbirth, exercise and emotional stress.
The most serious cases, previously known as “type 1” and now classed as “primary” heart attacks, had previously prioritised those caused by a clot blocking blood flow to the heart.
Other forms can involve reduced blood flow for different reasons, including the tightening or tearing of coronary arteries. These can be more likely to be missed or treated less urgently.
The guidance also introduces a lower diagnostic threshold for women based on levels of troponin, a protein released into the blood when the heart is injured and damaged.
Previously, women were expected to meet the same troponin threshold as men to receive a diagnosis.
Williams said the streamlined heart attack categories would also help patients understand the cause of their heart attack and what comes next.
The three upgraded types are coronary artery spasm, coronary embolism and spontaneous coronary artery dissection (SCAD).
Coronary artery spasm involves the tightening of an artery, which can deprive the heart muscle of blood and oxygen. It can be caused by emotional stress, exercise or extreme cold.
Coronary embolism occurs when a blood clot or fatty deposit travels to a coronary artery and causes a blockage.
SCAD is caused by a tear in a coronary artery. Around 80 per cent of cases occur in women, and it often happens during or soon after pregnancy.
Professor Nicholas Mills, a cardiologist at the University of Edinburgh who led the international taskforce behind the guidance, said it was “the first time that we’ve had a truly global approach to aligning how we diagnose what is probably the most important diagnosis there is”.
He said: “It kills so many people, and we’ve never got everyone together around the world to agree how we’re going to describe it, classify it, explain it to our patients.
“Our job now is to implement this as widely as possible. It’s just as relevant for the UK as it is for any other country around the world. It is a revolution. It’s going to make care better for patients.”
Mills said there had been “unintended systematic bias against women”, including through the use of the key blood test for diagnosing heart attacks at an average level, which picks up all men but misses some women.
He said: “This is used for all types of heart attack in every emergency department in the world, and we want to make sure that it’s used correctly.”
The guidance was drawn up by the ESC, the American College of Cardiology, the American Heart Association and the World Heart Federation.
Entrepreneur2 weeks agoKOVE Medical raises €1.7 million to improve safety of foetal surgery
Pregnancy2 weeks agoUK study aims to transform maternity care for high-risk pregnancies
Pregnancy4 days agoParacetamol use may impact future fertility, studies suggest
Events1 week agoLast chance to save on Women’s Health Week and Women’s Sport Summit: Early Bird pricing ends 11 September
Menopause2 weeks agoMenopause hormone treatment may ease brain fog, study suggests
Menopause6 days agoCancer drug could tackle osteoporosis menopause weight gain
News2 weeks agoSpanish agency criticised for menopause guidelines based on male studies
Fertility2 weeks agoNHS IVF access review launched in Scotland