Insight
Changes in AI mammogram risk scores help predict future breast cancer

Changes in AI mammogram scores may help predict breast cancer years before diagnosis, research involving more than 54,000 women suggests.
Scores rose steadily among women who later developed the disease but remained broadly stable among those who did not.
The increase could be detected up to six years before diagnosis and became much steeper during the final two years.
Researchers led by Professor Constance Lehman, of Harvard Medical School and healthcare technology company Clairity, analysed screening mammograms taken between 2009 and 2019.
They used a validated, open-source deep learning model to calculate five-year breast cancer risk scores from the images alone.
Deep learning is a form of artificial intelligence trained to recognise complex patterns in large amounts of data.
The model examined the whole mammogram rather than relying on a limited, predetermined feature such as breast density.
Models of this kind have performed better than traditional risk models and breast density alone when estimating a woman’s five-year breast cancer risk.
The study initially included 239,703 consecutive two-dimensional screening mammograms from 89,882 patients across six imaging sites spanning urban tertiary, community-based and rural settings.
All were standard bilateral full-field digital mammography examinations, taken with or without digital breast tomosynthesis.
Digital breast tomosynthesis uses multiple low-dose X-ray images to create a three-dimensional view of the breast.
After exclusions, the final analysis involved 54,014 women with a median age of 61 and a total of 158,807 mammograms.
Each woman contributed one index examination and up to six previous annual mammograms. Women had a median of three scans each.
For women who developed cancer, the index examination was their final screening mammogram within the year before diagnosis. For the cancer-free group, it was their final mammogram during the five-year study period.
The model did not use demographic information, clinical records or historical imaging data when calculating each score.
Of the women included, 817, or one per cent, were diagnosed with breast cancer within 365 days of their index examination.
This included 451 women, or 55 per cent, with invasive breast cancer and 118, or 14 per cent, with ductal carcinoma in situ, known as DCIS.
DCIS occurs when abnormal cells are found inside a milk duct but have not spread into the surrounding breast tissue.
The cancer type was unknown for the remaining 248 patients, representing 30 per cent of the cancer group.
A total of 682 cancers, or 83 per cent, were detected through screening, while 135, or 17 per cent, were interval cancers diagnosed between routine mammograms.
The other 53,197 women were not diagnosed with breast cancer during follow-up and formed the cancer-free comparison group.
Professor Lehman said: “We observed clinically relevant differences in risk trajectories between women who did and did not develop cancer. The increase in scores among cancer patients was detectable as early as six years prior to diagnosis and became more pronounced over time.”
Among women later diagnosed with the disease, the median score rose from 2.1 five to six years before diagnosis to 6.6 at the index examination.
Scores among cancer-free women remained stable, with median values ranging from 1.8 to 2.2 throughout the study.
The rise among women who developed cancer was steepest during the two years before their index examination.
Professor Lehman said: “These findings demonstrate signals, invisible to the human eye, in the image alone can predict future risk. This is exciting, because 85 per cent of women diagnosed with breast cancer do not have a significant family history of breast cancer or known genetic mutations.”
Most breast cancers are considered sporadic, meaning they are not driven by inherited genetic changes or a family history of the disease.
Traditional risk models have a limited ability to distinguish between women who will and will not develop breast cancer when used across large screening populations.
Researchers said tracking how scores change over time could provide more information than calculating risk at a single appointment.
Professor Lehman said: “AI-derived risk scores can identify patients who are otherwise predisposed to the disease, and our findings demonstrate that image-based AI risk scores evolve over time and that changes in those scores may provide additional information about future breast cancer risk.”
The patterns remained consistent when women were grouped by age and breast density.
Breast density describes the amount of fibrous and glandular tissue visible on a mammogram. Dense tissue can make cancers harder to detect and is also associated with an increased risk of the disease.
Researchers said image-based scores could support personalised screening and risk-reduction strategies without relying on self-reported or inconsistent clinical information.
Professor Lehman said: “These trends remained robust across subgroups defined by age and breast density, further supporting the generalisability of our findings. This is particularly relevant given persistent disparities in screening performance across patient populations. A dynamic biomarker approach grounded in the imaging data could mitigate some of these disparities by enabling risk-based personalisation that does not rely on self-reported or inconsistent clinical data.”
A biomarker is a measurable sign that can indicate a person’s health, disease risk or response to treatment.
Changing scores could eventually help clinicians identify women who may benefit from additional imaging or measures intended to reduce their risk.
Professor Lehman said: “With the power of AI, computer vision, and the ability to extract predictive data, we are able to apply the power of imaging to risk assessment and preventing disease from developing. Having a dynamic risk score opens up a whole new domain of more effective preventive therapies for breast cancer, similar to how we screen for and treat patients with high cholesterol and hypertension.”
AI image-based risk scores are included in the 2026 National Comprehensive Cancer Network guidelines.
The guidelines recommend that, from the age of 35, women with an elevated five-year risk score of more than 1.7 per cent consider breast MRI alongside annual mammography.
An AI image-based model approved by the US Food and Drug Administration is already being used to calculate five-year breast cancer risk at selected US healthcare institutions.
Fertility & pregnancy
Trust apologises for ‘human error’ after maternity data loss

Nottingham University Hospitals NHS Trust has apologised after a human error caused 11 years of maternity data to be overwritten.
The incident happened during routine technical work on 18 August, when computer instructions intended to create a copy of a radiotherapy database were mistakenly applied to the maternity database.
Most of the affected information has since been recovered, including notes, observations, test results and other information recorded as part of patient care.
However, the trust has been unable to fully restore the historical record showing who viewed maternity records between September 2011 and November 2022.
Current data was not affected and the incident has had no impact on current maternity services or care provided to women and babies, according to the trust.
It also said no information was accessed or used inappropriately as a result of the incident.
Andy Callow, chief digital and information officer at Nottingham University Hospitals, said: “I am sorry for the concern and distress this incident may cause to women and families affected.
“On 18 August 2026, a human error during a routine technical process resulted in a maternity records database being unintentionally overwritten.
“We took immediate action to investigate the incident and recover the affected information.
“The information needed to support patient care has been restored and there has been no impact on current maternity services or the care provided to women and babies today.
“However, to date, we have been unable to fully restore the historical record showing who viewed maternity records between September 2011 and November 2022.
“We have informed the Information Commissioner’s Office, completed a full investigation and strengthened our processes and controls to help prevent a similar incident from happening again.”
The error occurred when pre-written computer instructions previously used for another hospital system were used during the technical work.
A setting that should have been changed was not altered, resulting in work being carried out on the maternity database instead of the radiotherapy database.
The issue was escalated within minutes of being identified and experts were brought in to recover as much information as possible.
The trust has referred the incident to the Information Commissioner’s Office and notified Nottinghamshire Police, which is conducting a separate criminal investigation into maternity care at the trust.
The force is assessing whether the loss of information about who accessed maternity records could affect that investigation.
The incident follows a maternity review led by midwife Donna Ockenden, which concluded in June after examining the cases of 2,500 families over a 20-year period.
The review found more than 500 mothers and babies suffered potentially avoidable harm, with 162 dying following substandard care. Some babies who survived were left seriously disabled.
Nottinghamshire Police announced its separate criminal investigation, Operation Perth, in September 2023.
Insight
Charity launches Women’s Health Plan to tackle inequalities in long-term conditions

Chest Heart & Stroke Scotland has launched a three-year Women’s Health Plan setting out actions to improve prevention, diagnosis, treatment and support for women in Scotland.
The 2026 to 2029 plan includes commitments on health information, prevention and early detection, professional training, peer support, post-diagnosis care, policy and research.
It comes amid disparities affecting women with chest, heart and stroke conditions, including differences in diagnosis, testing and treatment.
Figures cited by the charity show women in Scotland are 50 per cent more likely than men to receive an initial misdiagnosis after a heart attack.
Jane-Claire Judson, chief executive of Chest Heart & Stroke Scotland, said: “Women have been telling us for years that their symptoms aren’t being taken seriously, and the evidence backs them up.
“When we talk about women’s health, we need to look beyond reproductive and maternal health alone.
“Women experience inequalities across a wide range of conditions, including chest, heart, stroke and Long Covid conditions, and they deserve equitable access to the information, support and care they need.
“Our CHSS Women’s Health Plan is about listening to those experiences and turning them into meaningful action.”
Across the UK, women are twice as likely to be misdiagnosed with heart failure, with many waiting an average of 20 weeks for a diagnosis, compared with 3.6 weeks for men.
There are more than 4,600 incidences of stroke in women in Scotland each year, with more than 1,200 dying as a result.
Asthma and chronic obstructive pulmonary disease (COPD) are also more common among women, while women are nearly twice as likely as men to die from asthma.
Women are less likely to be offered diagnostic testing within 72 hours of a heart attack and less likely to be prescribed medication that reduces the risk of a second heart attack, according to the charity.
CHSS also said conditions that predominantly affect women, including Long Covid and heart conditions such as coronary microvascular dysfunction, remain under-researched and under-diagnosed.
Four in five women say they are not listened to by healthcare professionals, while UK female life expectancy has fallen from 20th to 26th place among 38 OECD countries in recent years.
The Women’s Health Plan includes developing women-specific health information and launching a prevention and early detection programme through CHSS’s Health Defence and Community Healthcare Support Service.
Other commitments include raising the visibility of women’s health, strengthening training for healthcare professionals, CHSS colleagues and volunteers, expanding peer support and post-diagnosis care, and campaigning for changes to policy, funding and women’s inclusion in research.
The charity also plans to drive continuous improvement in its women’s health work, shaped by lived experience.
CHSS said it will seek to address inequalities through prevention programmes, professional education, policy influence and improved support for women across Scotland.
The plan builds on CHSS’s women’s health work launched in 2021 and its wider No Life Half Lived strategy. It also aligns with phases one and two of the Scottish Government’s Women’s Health Plan.
More than 140 responses to a national survey helped shape the plan, alongside consultation with health and social care professionals and people with lived experience through CHSS’s Voices of Experience Panel.
Judson said: “By improving awareness, supporting earlier detection and diagnosis, and ensuring women are heard when they seek help, we can begin to address inequalities that have persisted for far too long.
“Our first plan, launched in 2021, established important foundations.
“This next phase builds on that progress and reflects our commitment to a Scotland, where nobody is left behind because of their sex or gender.
“At Chest Heart & Stroke Scotland, our No Life Half Lived mission means working towards a future where everyone can live well with their condition. By bringing together women with lived experience, health professionals, policymakers and partners, we can create lasting change and help build a fairer, healthier Scotland for women.”
News
EU healthcare’s gender pay gap hits 19%, WHO report finds

Women in Europe’s health and care sector face a 19 per cent hourly gender pay gap, according to a new World Health Organization (WHO) report.
Women account for 77 per cent of the sector’s workforce, compared with 45 per cent across all other sectors combined, but make up only 55 per cent of its top earners.
The hourly gender pay gap widens at higher wage levels, from 2 per cent among the lowest earners to more than 22 per cent at the top.
The WHO report found that health and care accounts for almost 17 per cent of all women’s employment in its European Region, compared with 5 per cent of men’s employment.
The sector is the fourth-largest employer overall and the single largest employer of women in the region.
Natasha Azzopardi Muscat, director of the Division for Health Systems at WHO Europe, said: “Women make up the majority of the people who keep Europe’s health systems running, yet they’re paid less than their male counterparts, a gap that compounds over a lifelong career.”
The findings follow a pattern seen across the wider labour market, with structural inequality increasing at higher wage and seniority levels.
Globally, women working in health earn an average of 24 per cent less than men, according to the report, a wider gap than in many other industries.
Some of the difference in pay could be explained by work-related factors, including age, education, public or private sector employment and whether people worked full-time or part-time.
After adjusting for those four factors, the hourly pay gap fell from 19 per cent to 6 per cent, while the monthly gap declined from 28 per cent to 10 per cent.
The remaining difference could not be explained by factors measured in the data.
“Most of this gap isn’t down to women working fewer hours, being younger or working in different parts of the sector,” Azzopardi Muscat said.
“It comes down to how the sector values women’s work. Age, education, working hours and public versus private sector employment only helps explain some of it.”
WHO said the findings point to factors including the undervaluation of care work, occupational segregation and potential discrimination in pay-setting practices.
Occupational categories with a higher proportion of women paid less across managerial, professional and technical roles.
Management jobs in health and care employ more women than management roles in other sectors and pay an average of €22 per hour, compared with €24.70 in comparable roles elsewhere.
WHO described the gender pay gap as one of the most persistent forms of labour market inequality. Given the number of women working in health and care, it said the gap could have important economic and social consequences.
The report said the inequality may lead to lower lifetime earnings and pension entitlements, increase women’s risk of poverty, reduce returns to education and undermine sustainable economic growth.
“It means lower pensions, less financial security in older age, and a higher risk of poverty for women who’ve spent their working lives caring for others,” said Azzopardi Muscat.
“This isn’t a coincidence, and it isn’t about qualifications. Women are being paid less for the same work and passed over for the roles that pay more.”
WHO said closing gender pay gaps was both an equity imperative and an investment in a stronger and more sustainable health workforce.
It suggested measures including greater salary transparency, increased female representation in decision-making roles and action to address gender norms and stereotypes.
Diagnosis2 days agoTrust to decide how far back to review unnecessary breast cancer surgeries
Researcher / academic3 days agoNew test could cut need for invasive womb cancer checks
Healthy ageing5 days agoHigher BMI in early adulthood linked to lower breast cancer risk after menopause
Business & startups4 days agoPersonalising women’s health with AI
Pregnancy2 days agoUK commits £254m to boost women’s maternal healthcare choices
Menstrual & gynaecological health4 days agoMira launches at-home cortisol tracking kit
Researcher / academic4 days agoTargeted nanotherapy shows endometriosis promise
News5 days agoEU healthcare’s gender pay gap hits 19%, WHO report finds











3 Comments