(Press-News.org) First full results of a randomised trial investigating the use of AI in a national breast cancer screening programme finds AI-supported mammography screening is more effective across many measures than standard mammography.
AI-supported breast cancer screening identified more women with clinically relevant cancers during the screening without a higher rate of false positives.
Additionally, women who underwent AI-supported screening were less likely to be diagnosed with more aggressive and advanced breast cancer in the two years following.
Authors say these findings could justify implementing AI in mammography screening programmes, particularly in the context of health professional workforce shortages.
Artificial intelligence (AI)-supported mammography identifies more cancers during screening and reduces the rate of breast cancer diagnosis by 12% in the years following, finds the first randomised controlled trial of its kind involving over 100,000 Swedish women published in The Lancet journal.
The interim safety results of the MASAI trial, published in The Lancet Oncology in 2023 [1], found a 44% reduction in screen-reading workload for radiologists. Additionally, a different early analysis of the trial published in The Lancet Digital Health [2], found a 29% increase in cancer detection without an increase in false positives.
The full results of the trial, published today, show AI-supported mammography also reduces cancer diagnoses in the years following a breast cancer screening appointment by 12% – a key test of screening programme effectiveness.
Lead author Dr Kristina Lång from Lund University, Sweden, says “Our study is the first randomised controlled trial investigating the use of AI in breast cancer screening and the largest to date looking at AI use in cancer screening in general. It finds that AI-supported screening improves the early detection of clinically relevant breast cancers which led to fewer aggressive or advanced cancers diagnosed in between screenings.
“Widely rolling out AI-supported mammography in breast cancer screening programmes could help reduce workload pressures amongst radiologists, as well as helping to detect more cancers at an early stage, including those with aggressive subtypes.
“However, introducing AI in healthcare must be done cautiously, using tested AI tools and with continuous monitoring in place to ensure we have good data on how AI influences different regional and national screening programmes and how that might vary over time.”
Mammography screening has been associated with a lower breast cancer death rate, largely due to the early detection and treatment of the cancer. However, despite European guidelines recommending two radiologists read mammograms, some cancers still go undetected in screening.
Estimates suggest that 20-30% of breast cancers diagnosed after a negative screen and before the next scheduled screen (interval cancers) could have been spotted at the preceding mammogram. Interval cancers are often more aggressive or advanced than cancers detected during routine screening, making them harder to treat effectively.
Previous observational studies and interim results of this trial have found AI-supported mammography increases breast cancer detection compared with standard screening, however a key question has been if this increase in breast cancer detection translates into a reduction in interval cancers.
Between April 2021 and Dec 2022, over 100,000 women who were part of mammography screening at four sites in Sweden were randomly assigned to either AI-supported mammography screening (intervention arm) or to standard double reading by radiologists without AI (control arm). Double reading, where two radiologists read each mammogram, is standard practice in European screening programmes.
In the intervention arm, a specialist AI system analysed the mammograms and triaged low-risk cases to single reading and high-risk cases to double reading performed by radiologists. AI was also used as detection support to the radiologists, in which it highlighted suspicious findings in the image.
The AI system was trained, validated, and tested with more than 200,000 examinations from multiple institutions across more than ten countries.
During the two years follow up, there were 1.55 interval cancers per 1,000 women (82/53,043) in the AI-supported mammography group, compared to 1.76 interval cancers per 1,000 women (93/52,872) in the control group: a 12% reduction in interval cancer diagnosis for the AI arm.
Additionally, there were 16% fewer invasive (75 v 89), 21% fewer large (38 v 48), and 27% fewer aggressive sub-type cancers (43 v 59) in the AI group compared to the control arm.
In the AI-supported mammography group, 81% of cancer cases (338/420) were detected at screening, compared to 74% of cancer cases (262/355) in the control group: a 9% increase. The rate of false positives was similar for both groups, at 1.5% in the intervention group and 1.4% in the control group.
First author Jessie Gommers, PhD student, Radboud University Medical Centre, Netherlands, says, "Our study does not support replacing healthcare professionals with AI as the AI-supported mammography screening still requires at least one human radiologist to perform the screen reading, but with support from AI. However, our results potentially justify using AI to ease the substantial pressure on radiologists’ workloads, enabling these experts to focus on other clinical tasks, which might shorten the waiting times for patients.”
The authors note several limitations including that the analysis was conducted in one country (Sweden), was limited to one type of mammography device and one AI system which might limit the generalisability of the results. Additionally, in this trial, radiologists were moderately to highly experienced, which could limit the generalisability of the findings to less experienced radiologists. Lastly, information on race and ethnicity was not collected.
Dr Lång says, “Further studies on future screening rounds with this group of women and cost-effectiveness will help us understand the long-term benefits and risks of using AI-supported mammography screening. If they continue to suggest favourable outcomes for AI-supported mammography screening compared with standard screening, there could be a strong case for using AI in widespread mammography screening, especially as we face staff shortages.”
NOTES TO EDITORS
This study was funded by the Swedish Cancer Society, Confederation of Regional Cancer Centres and Swedish governmental funding for clinical research. A full list of authors and their institutions are available in the paper.
The labels have been added to this press release as part of a project run by the Academy of Medical Sciences seeking to improve the communication of evidence. For more information, please see: http://www.sciencemediacentre.org/wp-content/uploads/2018/01/AMS-press-release-labelling-system-GUIDANCE.pdf if you have any questions or feedback, please contact The Lancet press office pressoffice@lancet.com
Quotes from Authors cannot be found in the text of the Article but have been supplied for the press release.
References:
1. https://www.thelancet.com/journals/lanonc/article/PIIS1470-2045(23)00298-X/fulltext
2. https://www.thelancet.com/journals/landig/article/PIIS2589-7500(24)00267-X/fulltext
END
The Lancet: AI-supported mammography screening results in fewer aggressive and advanced breast cancers, finds full results from first randomized controlled trial
2026-01-30
ELSE PRESS RELEASES FROM THIS DATE:
New AI tool improves treatment of cancer patients after heart attack
2026-01-30
Cancer patients who suffer a heart attack face a dangerous mix of risks, which makes their clinical treatment particularly challenging. As a result, patients with cancer have been systematically excluded from many clinical trials and available risk scores. Until now, doctors had no standard tool to guide treatment in this vulnerable group.
International study leverages population data
An international team led by researchers from the University of Zurich (UZH) has now developed the first risk prediction model designed specifically for cancer patients who have had a heart attack. The study, published in The Lancet, analyzed more than one million heart attack patients in England, Sweden ...
Kandahar University highlights global disparities in neurosurgical workforce and access to care
2026-01-29
Neurological disorders contribute to nearly nine million deaths globally each year, and an estimated 22.6 million new cases require neurosurgical attention annually, of which approximately 13.8 million require surgical intervention. Despite this burden, access to safe and timely neurosurgical care remains limited for more than two-thirds of the world’s population, particularly in low- and middle-income countries (LMICs). This gap has increasingly been recognized as a major global public health concern.
A new article, published on November 20, 2025, in the ...
Research spotlight: Discovering risk factors for long-term relapse in alcohol use disorder
2026-01-29
John F. Kelly, PhD, of the Recovery Research Institute and Department of Psychiatry at Mass General Brigham, is the lead author of a paper published in Frontiers in Public Health, “Long-term relapse: markers, mechanisms, and implications for disease management in alcohol use disorder.”
Q: What challenges or unmet needs make this study important?
Alcohol use disorder (AUD) is one of leading causes of preventable death in the United States and worldwide, and leads to substantial disease and medical complication. While treatments are available that can help ...
As fossil fuel use declines, experts urge planning and coordination to prevent chaotic collapse
2026-01-29
As the world shifts toward renewable energy sources, some experts warn that a lack of planning for the retirement of fossil fuels could lead to a disorderly and dangerous collapse of existing systems that could prolong the transition to green energy.
In a study published in the journal Science, University of Notre Dame researchers Emily Grubert and Joshua Lappen argue that fossil fuel systems might be far more fragile than current energy models assume.
“Systems designed to be large and growing behave differently when they shrink,” said Grubert, associate professor of sustainable energy policy at ...
Scientists identify the antibody's hinge as a structural "control hub"
2026-01-29
The lower hinge of immunoglobulin G (IgG), an overlooked part of the antibody, acts as a structural and functional control hub, according to a study by researchers at Science Tokyo. Deleting a single amino acid in this region transforms a full-length antibody into a stable half-IgG1 molecule with altered immune activity. The findings provide a blueprint for engineering next-generation antibody therapies with precisely tailored immune effects for treating diseases such as cancer and autoimmune diseases.
Antibodies are Y-shaped proteins that help the immune system recognize and eliminate foreign threats such as bacteria and viruses. ...
Late-breaking study establishes new risk model for surgery after TAVR
2026-01-29
NEW ORLEANS — January 29, 2026 — At the 2026 Society of Thoracic Surgeons (STS) Annual Meeting, investigators will present a late-breaking study focused on surgical aortic valve replacement (SAVR) following prior transcatheter aortic valve replacement (TAVR), a clinical scenario increasingly encountered as TAVR use expands. The analysis draws on data from the STS Adult Cardiac Surgery Database to characterize risk over time and to validate a dedicated STS risk model designed to support decision-making for patients requiring surgery after TAVR.
The study, to be ...
To reduce CO2 emissions, policy on carbon pricing, taxation and investment in renewable energy is key
2026-01-29
A new peer-reviewed study evaluating climate policies in 40 countries over a 32-year period finds that carbon pricing and taxation—combined with investments in renewable energy and research—are among the most effective tools governments can use to reduce CO₂ emissions.
Drawing on successful examples such as Sweden and Norway, which have implemented a broad mix of climate policies at varying levels of stringency, the authors conclude that countries benefit most from a comprehensive and diverse policy toolkit rather than reliance on a single measure.
The research team—comprising experts from the University of Barcelona, ...
Kissing the sun: Unraveling mysteries of the solar wind
2026-01-29
Using data collected by NASA's Parker Solar Probe during its closest approach to the sun, a University of Arizona-led research team has measured the dynamics and ever-changing "shell" of hot gas from where the solar wind originates.
Published in Geophysical Research Letters, the findings not only help scientists answer fundamental questions about energy and matter moving through the heliosphere – the volume of space controlled by the sun's activity – which affects not just the Earth and moon, but all ...
Breathing new life into nanotubes for a cooler planet
2026-01-29
The fight against climate change relies heavily on finding better ways to capture carbon dioxide before it escapes into our atmosphere. While carbon nanotubes have long been seen as a "wonder material" for this task, their internal structures are often locked away like a closed pipe. Now, a research team from the Skolkovo Institute of Science and Technology (Skoltech) has pioneered a deceptively simple way to pop those caps open and supercharge their adsorption capacity.
In a study published in Carbon Research, the team reveals that a straightforward thermal treatment, essentially "baking" single-walled carbon nanotubes (SWCNTs) in ambient air, can ...
Machine learning reveals how to maximize biochar yield from algae
2026-01-29
Researchers have developed a powerful machine learning framework that can accurately predict and optimize biochar production from algae, offering a faster and more sustainable path toward carbon rich materials for climate mitigation, soil improvement, and environmental applications.
Biochar is a solid, carbon rich product created when biomass is heated in low oxygen conditions. It has attracted global attention for its ability to store carbon long term, improve soil health, and support renewable energy systems. While most biochar is made from wood or agricultural residues, algae are emerging as ...