Nationwide real-world implementation of AI for cancer detection in population-based mammography screening
Open accessThe DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.
Abstract
Artificial intelligence (AI) in mammography screening has shown promise in retrospective evaluations, but few prospective studies exist. PRAIM is an observational, multicenter, real-world, noninferiority, implementation study comparing the performance of AI-supported double reading to standard double reading (without AI) among women (50–69 years old) undergoing organized mammography screening at 12 sites in Germany. Radiologists in this study voluntarily chose whether to use the AI system. From July 2021 to February 2023, a total of 463,094 women were screened (260,739 with AI support) by 119 radiologists. Radiologists in the AI-supported screening group achieved a breast cancer detection rate of 6.7 per 1,000, which was 17.6% (95% confidence interval: +5.7%, +30.8%) higher than and statistically superior to the rate (5.7 per 1,000) achieved in the control group. The recall rate in the AI group was 37.4 per 1,000, which was lower than and noninferior to that (38.3 per 1,000) in the control group (percentage difference: −2.5% (−6.5%, +1.7%)). The positive predictive value (PPV) of recall was 17.9% in the AI group compared to 14.9% in the control group. The PPV of biopsy was 64.5% in the AI group versus 59.2% in the control group. Compared to standard double reading, AI-supported double reading was associated with a higher breast cancer detection rate without negatively affecting the recall rate, strongly indicating that AI can improve mammography screening metrics.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
International evaluation of an AI system for breast cancer screening
McKinney, S. M., Sieniek, M., Godbole, V., Godwin, J., Antropova, N., Ashrafian, H., Back, T., Chesus, M., Corrado, G. S., Darzi, A., et al. (2020) · Nature · doi:10.1038/s41586-019-1799-6 · Cited by 3,287
Robust causal inference using directed acyclic graphs: the R package ‘dagitty’
Textor, J., van der Zander, B., Gilthorpe, M. S., Liśkiewicz, M., & Ellison, G. T. H. (2017) · International Journal of Epidemiology · doi:10.1093/ije/dyw341 · Cited by 2,295 · cited 1×
“All analyses were conducted with R (version 4.1.3) using the packages PSweight (version 1.2.0) 24 , dagitty (version 0.3.1) 26 and marginaleffects (version 0.18) 27 , as well as Python (version 3.10) 28 using the package dowhy (version 0.11.1) 29 .”
InfluentialPrinciples of confounder selection
VanderWeele, T. J. (2019) · European Journal of Epidemiology · doi:10.1007/s10654-019-00494-6 · Cited by 1,535
Addressing extreme propensity scores via the overlap weights
Li, F., & Thomas, L. E. (2018) · American Journal of Epidemiology · doi:10.1093/aje/kwy201 · Cited by 694 · cited 3×
“The empirical sandwich variance for propensity score weighting estimators was used 23,24 .”
Rodriguez-Ruiz, A., Lång, K., Gubern-Merida, A., Broeders, M., Gennaro, G., Clauser, P., Helbich, T. H., Chevalier, M., Tan, T., Mertelmeier, T., et al. (2019) · JNCI: Journal of the National Cancer Institute · doi:10.1093/jnci/djy222 · Cited by 692
Lång, K., Josefsson, V., Larsson, A.-M., Larsson, S., Högberg, C., Sartor, H., Hofvind, S., Andersson, I., & Rosso, A. (2023) · The Lancet Oncology · doi:10.1016/s1470-2045(23)00298-x · Cited by 598 · cited 5×
“The MASAI (MAmmography Screening with AI) trial 15 , the ScreenTrustCAD study 16 and a study by Ng et al. 17 all reported increased cancer detection for work-flows incorporating AI, but the results on recall rates were inconsistent.”
InfluentialAnticipating artificial intelligence in mammography screening: views of Swedish breast radiologists
Högberg, C., Larsson, S., & Lång, K. (2023) · BMJ Health & Care Informatics · doi:10.1136/bmjhci-2022-100712 · Cited by 28
Cited by
The impact of AI on modern oncology from early detection to personalized cancer treatment
Li, J., Zhang, L., Yu, Z., Bao, Z., Li, D., & Wang, L. (2026) · npj Precision Oncology · doi:10.1038/s41698-026-01276-6 · Cited by 24
“118 , 463,094 women underwent screening, of whom 260,739 were examined with AI support by 119 radiologists.”
The economics of diagnostic safety
Slawomirski, L., Kelly, D., de Bienassis, K., Kallas, K.-A., & Klazinga, N. (2025) · OECD Health Working Papers · doi:10.1787/fc61057a-en · Cited by 20
Metadata
- Authors
- Eisemann, N., Bunk, S., Mukama, T., Baltus, H., Elsner, S. A., Gomille, T., Hecht, G., Heywang-Köbrunner, S., Rathmann, R., Siegmann-Luz, K., Töllner, T., Vomweg, T. W., Leibig, C., & Katalinic, A.
- Venue
- Nature Medicine
- Published
- 2025-01-07
- Volume
- 31
- Issue
- 3
- Pages
- 917-924
- ISSN
- 1078-8956 (ISSN-L)
- 1546-170X
- OpenAlex
- W4406150594
- Cited by
- 217
- References
- 7
- FWCI
- 90.30
- Type
- journal article
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Nationwide real-world implementation of AI for cancer detection in population-based mammography screening. https://app.cochat.ai/papers/10.1038/s41591-024-03408-6
- The paper
- Eisemann, N., Bunk, S., Mukama, T., Baltus, H., Elsner, S. A., Gomille, T., Hecht, G., Heywang-Köbrunner, S., Rathmann, R., Siegmann-Luz, K., Töllner, T., Vomweg, T. W., Leibig, C., & Katalinic, A. (2025). Nationwide real-world implementation of AI for cancer detection in population-based mammography screening. Nature Medicine. https://doi.org/10.1038/s41591-024-03408-6
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.