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.
Women are being urged to seek evidence-based advice and avoid menopause misinformation shared on social media.
A seminar co-hosted by the World Health Organization (WHO) mainly examined what is known about the cognitive effects of menopause and current research in the field worldwide.
Dr Nicole Jaff, a South African academic and certified menopause practitioner, said research into menopause and its effects was now at a peak.
She said: “There’s a lot of information out there.
“But I would say please look for the evidence-based information, not for the influencers and the misinformation, but those who are giving guidelines, who are giving information.”
Jaff highlighted research into cognitive changes during menopause and how some women experience brain fog, a term for difficulties with memory, concentration and clear thinking.
She said: “I’m very excited about the non-hormonal treatments that are now available, especially for women who could never take hormone therapy because of breast cancers and various cancers, who can now take it.
“I’m extremely excited about people who are standing up for evidence-based medicine, for science, who are actually fighting back against a lot of the social media and influencers who are not giving evidence-based information and making life very difficult for women because they think they should be forever young or buying this or buying that.”
Jaff advised women and healthcare workers to read new guidelines recently issued by the International Menopause Society. They are available free to download from its website.
The seminar also heard from Professor Aimee Spector, professor of clinical psychology of ageing at University College London.
She raised similar concerns about misinformation, particularly claims linking hormone replacement therapy, known as HRT, to dementia. Some claims suggest HRT reduces dementia risk, while others suggest it increases the risk.
Spector said: “I think there’s also lots of misinformation.
“And I think that there’s huge variations in how even professionals and doctors interpret this information.”
She was part of an international research team commissioned by the WHO last year to assess published studies on the issue.
The institutions involved also included the Global Brain Health Institute at Trinity College Dublin.
Spector said: “The first thing to say is that the quality of evidence was very low.
“Nine out of the 10 studies we looked at were observational, which means that you’re observing patterns over time. But you don’t necessarily know whether that’s due to the hormone therapy or not.
“Our overall recommendation was that there’s insufficient evidence for menopause hormone therapy in terms of either increasing or reducing the risk of dementia. In other words, we don’t know either way.”
Spector said women should therefore decide whether to use HRT to treat menopause symptoms rather than based on concerns about dementia.
She said: “It’s recommended for menopause symptoms, but it’s not recommended to reduce dementia. And I think a lot of people are saying that.”
The Menopause on the Brain webinar was part of an ongoing series hosted by the WHO and other global health agencies.
An endometriosis musical by two US writers will debut at the Edinburgh Festival Fringe in August.
“Endometriosis: The Musical” follows Jane, a woman trying to discover why she is living with chronic pain.
Maria Bartholdi and Kristin Stowell first developed the production for the 2022 Minnesota Fringe Festival.
The full show premiered at Theater in the Round in Minneapolis in 2025.
Stowell said the play drew on personal experience, although neither writer realised it at the time.
“So it’s like my goal to let women see themselves in this who are dealing with this and have a question they can bring back to their doctor,” she said.
“Like, could it be endometriosis?”
Bartholdi said she did not realise she might have the condition herself until after the play premiered.
“This show helped diagnose me, which I think is just one of the miraculous things that we hope this the show does for other people as well,” Bartholdi said.
Dr Wendy VanBuren, a radiologist at Mayo Clinic in Rochester, said she was a fan of the musical and its role in raising awareness of a common but underdiagnosed disease.
“Cells that are similar to but not identical to the cells that comprise the lining of the uterus, the inside of the uterus, are located outside the uterus,” said VanBuren.
“When they’re outside the uterus, there isn’t the right environment to deal with that. So basically, what you get is bleeding, and then you get inflammation.”
Roughly one in seven women live with the disease, and receiving a diagnosis can take nearly a decade.
Johnson & Johnson has offered an estimated US$5.5bn settlement covering about 76,000 claims that its talc products caused ovarian cancer.
The proposed agreement could end a contentious legal dispute over the company’s baby powder and other talc-based products that has lasted around a decade.
Johnson & Johnson said the settlement covers claims consolidated in a federal court in New Jersey and related cases in state court.
The claims represent nearly all the remaining talc cases against the US multinational, according to the company.
Johnson & Johnson has previously settled most claims alleging that its talc contained asbestos and caused mesothelioma.
Mesothelioma is a rare cancer affecting the lining of organs, most commonly the lungs, and is usually linked to asbestos exposure.
Law firms representing claimants confirmed the proposed deal, describing it as a good resolution after around 10 years of litigation.
The agreement must be accepted by 95 per cent of ovarian cancer claimants in state or federal court before it becomes final.
Erik Haas, vice-president of litigation at Johnson & Johnson, said the claims were “meritless” and that the company was willing to settle to bring the litigation to a close.
“While we are confident the company would have ultimately prevailed with further litigation, as it has in the vast majority of cases tried to date, this resolution allows the company to put this matter behind it and remain focused on its mission to develop medicines and devices that save lives,” Haas said.
The company expects to pay US$3bn in 2027, with further payments due in 2028.
The deal could be worth more, depending on how many people take part in the settlement.
Chris Seeger, a lawyer representing around 2,500 clients with talc claims who helped negotiate the agreement, said Johnson & Johnson could ultimately pay US$7bn or more.
The settlement assigns specific values to qualifying ovarian cancer claims but does not cap the company’s total payout.
“We got a fair settlement, and our clients are going to be happy with it,” Seeger said.
Johnson & Johnson reached the agreement after a series of court victories, including wins in individual trials and successful efforts to disqualify claimants’ lawyers from the litigation.
The company also secured court rulings against experts used by claimants to support their cases.
A federal judge last week questioned whether individual claimants could prove that talc had specifically caused their ovarian cancer.
Johnson & Johnson has consistently denied that its talc products caused cancer, maintaining that the products were safe and did not contain asbestos.
The company stopped selling talc-based baby powder in the US in 2020 and switched to a cornstarch-based product.
Litigation resumed in March 2025 after being paused for more than three years while Johnson & Johnson pursued a bankruptcy strategy known as the “Texas two step”.
The company filed three bankruptcies through a shell-company subsidiary in an attempt to settle the cases. Each bankruptcy was dismissed.
Before the bankruptcy attempts, Johnson & Johnson had a mixed record in talc trials.
These included a multibillion-dollar verdict for 22 women who said baby powder caused their ovarian cancer, alongside trials won by Johnson & Johnson and other verdicts later reduced on appeal.
Unlike the proposed bankruptcy settlements, the latest agreement applies only to existing claims and does not cover future lawsuits.
Seeger said excluding future claims made more money available for current claimants than the bankruptcy proposal and would allow all claims to be paid within 18 months rather than over more than a decade.
News3 days agoUK femtech investment surges 194% in a decade, research finds
Entrepreneur2 weeks agoFertility startup American Baby Company secures US$4m
Insight2 weeks agoNatural Cycles receives sixth FDA clearance for fertility algorithm
Wellness7 days agoCancer patient receives ‘landmark’ treatment in world-first
Insight2 weeks agoExperimental treatment significantly slows progression of fatal brain disease in women, study finds
Sponsored Content2 weeks agoThe room is filling up at WHW Europe 2026 with super early bird pricing ending this Friday
Insight1 week agoJohnson & Johnson offers to pay US$5.5bn to settle talc cancer lawsuits
News2 weeks agoPlanetary Health Diet lowers heart risk in older women, study finds
3 Comments