News
AI model could predict breast cancer risk without racial bias, study finds
The deep learning model has been shown to outperform traditional risk models in predicting a woman’s risk of developing breast cancer
A new AI model developed using mammogram image biomarkers could accurately predict both invasive and non-invasive forms of breast cancer without racial bias, new research has shown.
The findings, presented at the annual meeting of the Radiological Society of North America (RSNA), have suggested the model showed no bias across multiple races.
Traditional breast cancer risk assessment models use information obtained from patient questionnaires, such as medical and reproductive history, to calculate a patient’s future risk of developing breast cancer.
Data shows old models are more likely to demonstrate poor performance across different patient races, most likely due to the data used to develop the model.
“In the domain of precision medicine, risk-based screening has been elusive because we have not been able to accurately evaluate a woman’s risk of developing breast cancer,” said study lead author Leslie R. Lamb, a breast radiologist at Massachusetts General Hospital (MGH) in Boston.
“Even the best existing traditional risk models do not perform well on the individual level.
“Traditional models likely have racial biases due to the populations on which they were developed. Several of the commonly used models were developed on predominantly European Caucasian populations.”
According to the American Cancer Society, Black women demonstrate the lowest five-year relative survival rate for breast cancer among all racial and ethnic groups. This translates to a six per cent to eight per cent disparity in five-year survival rates between Black and white women across all breast cancer types.
The new deep learning AI risk assessment model developed using mammographic images has been shown to outperform traditional risk assessment models in future breast cancer development while also mitigating the racial biases seen in traditional models.
In the first study of its kind, Dr Lamb and colleagues assessed the performance of the image-based deep learning risk assessment model in predicting both future invasive breast cancer and non-invasive breast cancer across multiple races.
The study included 129,340 routine screening mammograms performed in 71,479 women between 2009 to 2018 with five-year follow-up data. Patient demographics were obtained from electronic medical records and instances of cancer were identified from the regional tumour registry.
The racial makeup of the study group included white, Black, Asian, self-reported and other races. The mean age of the women was 59 years old.
The deep learning model was shown to outperform traditional risk models in predicting a woman’s risk of developing early-stage, non-invasive breast cancer, also known as ductal carcinoma in situ (DCIS), as well as invasive breast cancer, known as invasive carcinoma.
“The model is able to translate the full diversity of subtle imaging biomarkers in the mammogram, beyond what the naked eye can see, that can predict a woman’s future risk of both DCIS and invasive breast cancer,” explained Lamb.
“The deep learning image-only risk model can provide increased access to more accurate, equitable and less costly risk assessment.”
Constance D. Lehman, senior author and breast radiologist at MGH, said: “This is a particularly exciting domain for AI, as it demonstrates the opportunity to apply ‘AI for good’—to reduce well-known racial disparities in risk assessment.
“We are now poised to translate these findings into improved clinical care for our patients.”
Ovarian cancer cases are rising among younger adults in England, with bowel cancer showing a similar pattern, a new study suggests.
Researchers said excess weight is a key contributor, but is unlikely on its own to explain the pattern.
The authors wrote: “These patterns suggest that while similar risk factors across ages are likely, some cancers may have age-specific exposures, susceptibilities, or differences in screening and detection practices.”
They added: “Although overweight and obesity are linked to 10 of the 11 cancers evaluated and account for a substantial proportion of cancer cases, both BMI-attributable and BMI-non-attributable incidence rates have increased, though the latter more slowly, suggesting other contributors.”
The study analysed cancer incidence, meaning new diagnoses, in England between 2001 and 2019 across more than 20 cancer types, comparing adults aged 20 to 49 with those aged 50 and over.
Among younger women, cases of 16 out of 22 cancers increased significantly over the period, while among younger men, 11 out of 21 cancers increased significantly.
In particular, there was a significant rise in 11 cancers with known behavioural risk factors among adults under 50. These were thyroid, multiple myeloma, liver, kidney, gallbladder, bowel, pancreatic, endometrial, mouth, breast and ovarian cancers.
Rates of all 11 also rose significantly among adults aged 50 and over, with the notable exceptions of bowel and ovarian cancer.
Five cancers, endometrial, kidney, pancreatic, multiple myeloma and thyroid cancer, increased significantly faster in younger than in older women, while multiple myeloma increased faster in younger than in older men.
The researchers looked at established risk factors including smoking, alcohol intake, diet, physical inactivity and body mass index, a measure used to assess whether someone is underweight, a healthy weight, overweight or obese.
With the exception of mouth cancer, all 11 cancers were associated with obesity. Six, liver, bowel, mouth, pancreatic, kidney and ovarian, were also linked to smoking.
Four, liver, bowel, mouth and breast, were associated with alcohol intake. Three, bowel, breast and endometrial, were linked to physical inactivity, and one, bowel, was associated with dietary factors.
But apart from excess weight, trends in those risk factors over the past one to two decades were stable or improving among younger adults.
That suggests other factors may also play a part, including reproductive history, early-life or prenatal exposures, and changes in diagnosis and detection.
The study noted that red meat consumption fell among younger adults, while fibre intake remained stable or slightly improved in both sexes between 2009 and 2019, although more than 90 per cent of younger adults were still not eating enough fibre in 2018.
Established behavioural risk factors accounted for a substantial share of cancer cases.
Excess weight was the risk factor associated with most cancers in 2019, ranging from 5 per cent for ovarian cancer to 37 per cent for endometrial cancer.
The researchers said the findings were based on observational data, meaning the study could identify patterns but could not prove cause and effect.
They also noted there were no consistent long-term national data for several risk factors, that the analysis was limited to England rather than the UK, and that cancer remains far more common overall in older adults despite the rise in cases among younger people.
Early miscarriage care after a first loss could prevent about 10,000 pregnancy losses a year in the UK, according to a new study.
The study by Tommy’s National Centre for Miscarriage Research and Birmingham women’s hospital involving 406 women found a 4 per cent reduction in the risk of future miscarriage for women on the graded model of care compared with usual care.
Women in England, Wales and Northern Ireland currently become eligible for specialised NHS care for early baby loss only after they have had at least three miscarriages.
Tommy’s has called for women to become eligible after one miscarriage, saying this could reduce the risk of future miscarriages and improve health outcomes for mothers.
Researchers said that would translate to 10,075 fewer miscarriages a year across the UK.
Kath Abrahams, chief executive of Tommy’s, said women were being “left without early access to services that could help prevent future losses and reduce the debilitating feelings of isolation and hopelessness that we know affect so many who experience pregnancy loss”.
She said: “Our pilot study indicates that providing support after a first miscarriage, with escalating care after further losses, is not only effective but achievable without significant additional workload for NHS teams who are already working extremely hard to deliver good care.
“Put simply, it is the right thing to do. We will do all we can to drive that change across the UK so that more women and families are supported after every miscarriage.”
The graded model of miscarriage care proposed by Tommy’s is already available in Scotland, and the charity is calling for it to be introduced across the whole of the UK.
The graded model includes nurse-led support after one miscarriage, with advice on reducing risk factors such as low vitamin D, folic acid intake, alcohol consumption and caffeine use.
Women who received the specialised care were 47 per cent more likely to have a risk factor identified and receive relevant advice to help prevent future miscarriages than women receiving usual care, the study found.
Among women who had experienced two miscarriages and received the specialised care, one in five were found to have thyroid dysfunction or anaemia, both conditions that can affect pregnancy outcomes.
About one in four pregnancies ends in miscarriage, most often within the first 12 weeks of pregnancy.
The report comes ahead of the long-awaited final findings of the government’s investigation into maternity care in England. Interim findings uncovered a range of failures, including claims that NHS hospitals that caused harm to women and babies during childbirth often resorted to a “cover-up” of their mistakes, falsified medical records and denied bereaved parents answers.
Women’s health minister Gillian Merron said: “Pregnancy and baby loss can have a devastating impact on women and families, who too often feel they have been left without the care and support they need.
“I welcome the findings of this important report, and this will be carefully considered as part of our ongoing work to make sure women get the high-quality, compassionate NHS care they deserve.”
Indian pharmaceutical giant Sun Pharma has agreed to buy Organon for US$11.75bn in a deal aimed at expanding its women’s health and biosimilars business.
Organon, which was spun out of Merck in 2021, has built a portfolio of more than 70 women’s health and general medicines products, including biosimilars, sold in the US and about 140 other countries.
The acquisition would give Sun Pharma a broader presence in biosimilars, which are medicines designed to be highly similar to existing biological drugs, and strengthen its position in women’s health.
Dilip Shanghvi, executive chairman of Sun Pharma, said: “Organon’s portfolio, capabilities, and global reach are highly complementary to our own, and we believe that bringing the two organizations together can create a stronger and more diversified platform.”
The companies said the combined business would generate annual revenue of US$12.4bn, operate across 150 countries and rank among the top three companies globally in women’s health.
They also said it would become the seventh largest biosimilar player.
Sun Pharma said the deal would help grow its innovative medicines business and expand its biosimilars offering.
It added that the combined company would have 18 large markets each generating more than US$100m in revenue.
Organon’s largest markets include the US, Brazil, Canada, China and countries in the European Union. The company also has six manufacturing facilities across the EU and emerging markets.
The deal follows market speculation that began on 10 April, when Indian media reported that Sun Pharma had submitted an all-cash offer for Organon.
A later report said the offer had been revised to US$13bn. Sun Pharma shares rose about 7 per cent on India’s National Stock Exchange after the announcement.
Sun Pharma said it would acquire all of Organon’s issued and outstanding shares in cash, using a combination of available cash and committed bank financing. It also estimated synergies of about US$350m within two to four years of completion.
The company said the acquisition would strengthen its cash generation, with EBITDA and cash flow set to nearly double, supporting efforts to reduce the net debt to EBITDA ratio of 2.3 times resulting from the deal. EBITDA is a measure of operating performance before certain costs are deducted.
Organon reported revenue of US$6.2bn last year and adjusted EBITDA of US$1.9bn. It also reported debt of US$8.64bn, down from US$9.5bn when it separated from Merck, and a cash balance of US$574m.
In November, Organon announced plans to sell its JADA System, designed to control and treat abnormal postpartum uterine bleeding or haemorrhage, to Laborie Medical Technologies for up to US$465m. Net proceeds from the sale will contribute to Organon’s cash balance as of 31 March 2026.
Organon will merge with a subsidiary of Sun Pharma, with Organon surviving the merger. The boards of both companies have approved the transaction.
Carrie Cox, executive chair of Organon, said: “Following a comprehensive review of strategic alternatives, our Board determined that this all-cash transaction offers compelling and immediate value to Organon stockholders.”
The transaction is expected to close in early 2027, subject to regulatory approvals and Organon stockholder approval.
Entrepreneur7 days agoFuture Fertility raises Series A financing to scale AI tools redefining fertility care worldwide
Entrepreneur4 weeks agoThree sessions that show exactly where women’s health is heading in 2026
Pregnancy4 weeks agoHow NIPT has evolved and what AI NIPT means in 2026
News4 weeks agoTwo weeks left to make your mark in women’s cardiovascular health
Fertility2 weeks agoFuture Fertility partners with Japan’s leading IVF provider, Kato Ladies Clinic
Mental health1 week agoLifting weights shows mental health and cognitive benefits in older women, study finds
Menopause2 weeks agoMore research needed to understand link between brain fog and menopause, expert says
News4 weeks agoCopper coil vs Mirena: Which is right for you?