{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T18:14:39Z","timestamp":1779300879489,"version":"3.51.4"},"reference-count":73,"publisher":"American Association for the Advancement of Science (AAAS)","issue":"850","funder":[{"name":"Swedish Cancer Society","award":["CAN2015\/649, 19 0267"],"award-info":[{"award-number":["CAN2015\/649, 19 0267"]}]},{"name":"Swedish Cancer Society","award":["19 0267"],"award-info":[{"award-number":["19 0267"]}]},{"name":"Swedish Cancer Society","award":["CAN2015\/649, 19 0267"],"award-info":[{"award-number":["CAN2015\/649, 19 0267"]}]},{"name":"Swedish Cancer Society","award":["19 0267"],"award-info":[{"award-number":["19 0267"]}]},{"DOI":"10.13039\/501100001862","name":"The swedish Research Council","doi-asserted-by":"crossref","award":["2022-06148"],"award-info":[{"award-number":["2022-06148"]}],"id":[{"id":"10.13039\/501100001862","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001862","name":"The swedish Research Council","doi-asserted-by":"crossref","award":["2022-06148"],"award-info":[{"award-number":["2022-06148"]}],"id":[{"id":"10.13039\/501100001862","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Stockholm County Council","award":["20200102"],"award-info":[{"award-number":["20200102"]}]},{"name":"Stockholm County Council","award":["20200102"],"award-info":[{"award-number":["20200102"]}]},{"name":"the Stockholm County Council","award":["4-2645\/2015, 20200102"],"award-info":[{"award-number":["4-2645\/2015, 20200102"]}]},{"name":"Mayo Clinic Comprehensive Cancer Center\/Cancer Research Karolinska Institutet Collaborative Cancer Research Program"},{"name":"Hoveida Family Foundation"},{"name":"Mayo Clinic Comprehensive Cancer Center\/Cancer Research Karolinska Institutet Collaborative Cancer Research Program","award":["-"],"award-info":[{"award-number":["-"]}]},{"name":"Hoveida Family Foundation","award":["-"],"award-info":[{"award-number":["-"]}]},{"name":"the Stockholm County Council","award":["4-2645\/2015, 20200102"],"award-info":[{"award-number":["4-2645\/2015, 20200102"]}]},{"name":"M\u00e4rit and Hans Rausings Initiative Against Breast Cancer","award":["-"],"award-info":[{"award-number":["-"]}]},{"name":"the Kamprad Foundation","award":["20150052"],"award-info":[{"award-number":["20150052"]}]},{"name":"M\u00e4rit and Hans Rausings Initiative Against Breast Cancer"},{"name":"the Kamprad Foundation","award":["20150052"],"award-info":[{"award-number":["20150052"]}]},{"name":"Research Council","award":["E0718301"],"award-info":[{"award-number":["E0718301"]}]},{"name":"Karolinska Assistant Professorship program","award":["2-1609\/2024"],"award-info":[{"award-number":["2-1609\/2024"]}]},{"name":"the Swedish Breast Cancer Association"},{"name":"and the Mayo Clinic Comprehensive Cancer Center\/Cancer Research Karolinska Institutet Collaborative Cancer Research Program"},{"name":"the Swedish Breast Cancer Association","award":["-"],"award-info":[{"award-number":["-"]}]},{"name":"the Mayo Clinic Comprehensive Cancer Center\/Cancer Research Karolinska Institutet Collaborative Cancer Research Program","award":["-"],"award-info":[{"award-number":["-"]}]},{"name":"Karolinska Assistant Professorship program","award":["2-1609\/2024"],"award-info":[{"award-number":["2-1609\/2024"]}]}],"content-domain":{"domain":["www.science.org"],"crossmark-restriction":true},"short-container-title":["Sci. Transl. Med."],"published-print":{"date-parts":[[2026,5,20]]},"abstract":"<jats:p>\n                    Image-derived artificial intelligence (AI) risk models have shown promise in short-term risk assessment for improving breast cancer (BC) screening. No image-derived long-term AI risk model for primary prevention has been developed and externally validated. Individuals aged 31 to 94 years were recruited between 2010 and 2020 in two population-based case cohorts (Olmsted County, Minnesota, US, and KARMA, Sweden) and one hospital-based case-control study (EMBED, Atlanta, US). Median follow-up in the case cohorts was 10 years, with BCs diagnosed through June 2022. Additional validation was performed in EMBED with 3-year follow-up. An AI risk model was developed in Sweden, and we report independent validation in Olmsted\/KARMA\/EMBED. Absolute 10-year risks were estimated at study entry. Time-dependent discriminatory performance [AUC(\n                    <jats:italic toggle=\"yes\">t<\/jats:italic>\n                    )] and expected-to-observed events (E\/O) were estimated. Comparisons were performed with clinical risk tools and the image-based Mirai tool. Across Olmsted\/KARMA, 8696 individuals (mean age, 54.4\u00b110.6) and 1633 individuals with incident BC (mean age, 57.0\u00b110.6) were included. Average 10-year risks were 3.83 and 3.14%, and E\/O ratios were 0.99 and 0.99. Ten-year AUC(\n                    <jats:italic toggle=\"yes\">t<\/jats:italic>\n                    ) for invasive BCs were 0.72 in Olmsted and 0.72 in KARMA. Similar discriminatory results were observed in EMBED. Our AI risk tool performed significantly better than Mirai in Olmsted\/KARMA\/EMBED. In KARMA, in the top 10% of high-risk individuals, the AI risk tool predicted 33% of BCs compared with 23%\/20%\/24% predicted by Tyrer-Cuzick-v8\/BCSC-v3\/Mirai (all\n                    <jats:italic toggle=\"yes\">P<\/jats:italic>\n                    \u00a0&lt;\u00a00.01). The 10-year image-derived AI risk model showed significantly higher performance than clinical risk models and Mirai in diverse populations, supporting its clinical potential for primary prevention.\n                  <\/jats:p>","DOI":"10.1126\/scitranslmed.ady7414","type":"journal-article","created":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T18:02:30Z","timestamp":1779300150000},"update-policy":"https:\/\/doi.org\/10.34133\/aaas_crossmark","source":"Crossref","is-referenced-by-count":0,"title":["A long-term image-derived AI-based risk model for primary prevention of breast cancer in individuals at high risk"],"prefix":"10.1126","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8135-4270","authenticated-orcid":true,"given":"Mikael","family":"Eriksson","sequence":"first","affiliation":[{"name":"Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, 17177 Stockholm, Sweden."},{"name":"Department of Public Health and Primary Care, University of Cambridge, CB21TN Cambridge, UK."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3233-5695","authenticated-orcid":true,"given":"Kamila","family":"Czene","sequence":"additional","affiliation":[{"name":"Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, 17177 Stockholm, Sweden."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1340-0647","authenticated-orcid":true,"given":"Christopher","family":"Scott","sequence":"additional","affiliation":[{"name":"Department of Quantitative Health Sciences, Mayo Clinic, Rochester, MN 55905, USA."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shawn","family":"Stoddard","sequence":"additional","affiliation":[{"name":"Department of Quantitative Health Sciences, Mayo Clinic, Rochester, MN 55905, USA."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hugh","family":"Smith","sequence":"additional","affiliation":[{"name":"Department of Radiology, Olmsted Medical Center, Rochester, MN 55905, USA."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5640-9126","authenticated-orcid":true,"given":"Per","family":"Hall","sequence":"additional","affiliation":[{"name":"Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, 17177 Stockholm, Sweden."},{"name":"Department of Oncology, S\u00f6dersjukhuset University Hospital, 11883 Stockholm, Sweden."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1962-9322","authenticated-orcid":true,"given":"Celine","family":"Vachon","sequence":"additional","affiliation":[{"name":"Department of Quantitative Health Sciences, Mayo Clinic, Rochester, MN 55905, USA."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"221","reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1590\/S0036-36342009000800003"},{"key":"e_1_3_2_3_2","first-page":"CD012191","article-title":"Risk-reducing medications for primary breast cancer: A network meta-analysis","volume":"4","author":"Mocellin S.","year":"2019","unstructured":"S. Mocellin, A. Goodwin, S. Pasquali, Risk-reducing medications for primary breast cancer: A network meta-analysis. Cochrane Database Syst. Rev. 4, CD012191 (2019).","journal-title":"Cochrane Database Syst. Rev."},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1093\/jnci\/djz226"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/S1470-2045(14)71171-4"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1158\/1940-6207.CAPR-16-0254"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1002\/sim.1668"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.22.02470"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41416-019-0476-8"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.22.01564"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1093\/ije\/dyw357"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1002\/sim.5958"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1177\/0093854816683956"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1002\/sim.6152"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.7326\/M15-2886"},{"key":"e_1_3_2_16_2","unstructured":"National Institute for Health and Care Excellence \u201cFamilial breast cancer: Classification care and managing breast cancer and related risks in people with a family history of breast cancer CG164\u201d (NICE 2013); www.nice.org.uk\/guidance\/cg164."},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1214\/19-STS729"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21225"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-014-3256-0"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.19.01472"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.6004\/jnccn.2015.0105"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41568-020-0266-x"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1634\/theoncologist.2017-0148"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1002\/cncr.25926"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1056\/NEJM198501173120303"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.3390\/cancers13020302"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1186\/bcr2942"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.22.02900"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.18.01779"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41571-020-0388-9"},{"key":"e_1_3_2_31_2","unstructured":"National Institute for Health and Care Excellence \u201cTirzepatide for managing overweight and obesity\u201d (NICE 2024); www.nice.org.uk\/guidance\/gid-ta11156\/documents\/html-content-8."},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.2021210097"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2019.20866"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1093\/ije\/dyx268"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.220047"},{"key":"e_1_3_2_36_2","unstructured":"E. A. Sickles \u201cACR BI-RADS\u00ae Atlas Breast imaging reporting and data system\u201d (American College of Radiology 2013) p. 39."},{"key":"e_1_3_2_37_2","unstructured":"US Food and Drug Administration \u201cMammography Quality Standards Act (MQSA) and MQSA Program\u201d (US Food and Drug Administration 2025); www.fda.gov\/radiation-emitting-products\/mammography-quality-standards-act-and-program."},{"key":"e_1_3_2_38_2","unstructured":"N. E. Breslow in Statistical Methods in Cancer Research Volume I: The Analysis of Case-Control Studies (International Agency for Research on Cancer 1980) pp. 248\u2013279."},{"key":"e_1_3_2_39_2","unstructured":"K. J. Rothman S. Greenland T. L. Lash Modern Epidemiology (Philadelpia Wolters Kluwer Health\/Lippincott Williams & Wilkins ed. 3 2008)."},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(07)61602-X"},{"key":"e_1_3_2_41_2","doi-asserted-by":"crossref","unstructured":"A. Howard R. Pang H. Adam Q. Le M. Sandler B. Chen W. Wang L.-C. Chen M. Tan G. Chu V. Vasudevan Y. Zhu \u201cSearching for MobileNetV3\u201d in 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) (IEEE 2019) pp. 1314\u20131324.","DOI":"10.1109\/ICCV.2019.00140"},{"key":"e_1_3_2_42_2","doi-asserted-by":"crossref","unstructured":"C. Szegedy V. Vanhoucke S. Ioffe J. Shlens Z. Wojna \u201cRethinking the inception architecture for computer vision\u201d in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (IEEE 2016) pp. 2818\u20132826.","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_3_2_43_2","doi-asserted-by":"crossref","unstructured":"T. Chen C. Guestrin \u201cXgboost: A scalable tree boosting system\u201d in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (Association for Computing Machinery 2016).","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2016.05.007"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953"},{"key":"e_1_3_2_46_2","unstructured":"D. P. Kingma J. Ba Adam: A method for stochastic optimization. arXiv:14126980 [cs.LG] (2014)."},{"key":"e_1_3_2_47_2","unstructured":"J. P. dos Reis Godinho Nvidia Corporation (NVDA) \u201cNvidia: Reshaping the foundations of tomorrow\u201d (Universidade NOVA de Lisboa 2022)."},{"key":"e_1_3_2_48_2","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke A.","year":"2019","unstructured":"A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, A. Desmaison, A. K\u00f6pf, E. Yang, Z. De Vito, M. Raison, A. Tejani, S. Chilamkurthy, B. Steiner, L. Fang, J. Bai, S. Chintala, Pytorch: An imperative style, high-performance deep learning library. Adv. Neural Inf. Proces. Syst. 32, 8024\u20138035 (2019).","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"e_1_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0100234"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(23)00113-9"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1972.tb00899.x"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2007.11.017"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10985-004-4771-0"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1958.10501452"},{"key":"e_1_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10549-018-4690-5"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13058-017-0820-y"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1136\/jmg-2022-108806"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1158\/1538-7445.AM2023-4174"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1126\/scitranslmed.aba4373"},{"key":"e_1_3_2_60_2","unstructured":"A. Yala Mirai Github (2025); https:\/\/github.com\/yala\/Mirai."},{"key":"e_1_3_2_61_2","unstructured":"A. Ehinger H. Lindman L. L\u00f6fgren L.-M. Petersson K. Sandelin \u00c5rsrapport 2015 fr\u00e5n Nationella Br\u00f6stcancerregistret (Regionalt Cancercentrum Stockholm Gotland 2016)."},{"key":"e_1_3_2_62_2","unstructured":"D. Grabau \u201cKVAST dokument br\u00f6sttum\u00f6rer: Svensk f\u00f6rening f\u00f6r patologi - Svensk f\u00f6rening f\u00f6r klinisk cytologi\u201d (Svensk f\u00f6rening f\u00f6r Patologi 2014)."},{"key":"e_1_3_2_63_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10654-017-0316-1"},{"key":"e_1_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1016\/S0895-4356(99)00102-X"},{"key":"e_1_3_2_65_2","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1176344247"},{"key":"e_1_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-017-0332-6"},{"key":"e_1_3_2_67_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.0006-341X.2000.00337.x"},{"key":"e_1_3_2_68_2","unstructured":"N. Howlader A. M. Noone M. Krapcho D. Miller A. Brest M. Yu J. Ruhl Z. Tatalovich A. Mariotto D. R. Lewis H. S. Chen E. J. Feuer K. A. Cronin KA SEER Cancer Statistics Review 1975\u20132017 (National Cancer Institute 2020); https:\/\/seer.cancer.gov\/csr\/1975_2017\/."},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1002\/1097-0258(20000730)19:14<1901::AID-SIM514>3.0.CO;2-V"},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1109\/66.382280"},{"key":"e_1_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-0258(19980430)17:8<857::AID-SIM777>3.0.CO;2-E"},{"key":"e_1_3_2_72_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1469-1809.1972.tb00293.x"},{"key":"e_1_3_2_73_2","unstructured":"Team RC R: A Language and Environment for Statistical Computing (R Foundation for Statistical Computing 2013)."},{"key":"e_1_3_2_74_2","doi-asserted-by":"crossref","unstructured":"R. A. Fisher \u201cStatistical methods for research workers\u201d in Breakthroughs in Statistics: Methodology and Distribution (Springer 1970) pp. 66\u201370.","DOI":"10.1007\/978-1-4612-4380-9_6"}],"container-title":["Science Translational Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.science.org\/doi\/pdf\/10.1126\/scitranslmed.ady7414","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T18:02:55Z","timestamp":1779300175000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.science.org\/doi\/10.1126\/scitranslmed.ady7414"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,20]]},"references-count":73,"journal-issue":{"issue":"850","published-print":{"date-parts":[[2026,5,20]]}},"alternative-id":["10.1126\/scitranslmed.ady7414"],"URL":"https:\/\/doi.org\/10.1126\/scitranslmed.ady7414","relation":{},"ISSN":["1946-6234","1946-6242"],"issn-type":[{"value":"1946-6234","type":"print"},{"value":"1946-6242","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,20]]},"assertion":[{"value":"2025-05-05","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-05","order":1,"name":"revised","label":"Revised","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-19","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-05-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"eady7414"}}