{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,5]],"date-time":"2026-09-05T07:41:25Z","timestamp":1788594085636,"version":"build-2803163510"},"reference-count":25,"publisher":"Oxford University Press (OUP)","issue":"8","license":[{"start":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T00:00:00Z","timestamp":1774483200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01 CA275074"],"award-info":[{"award-number":["R01 CA275074"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000005","name":"Department of Defense","doi-asserted-by":"publisher","award":["HT9425-23-1 to 0234"],"award-info":[{"award-number":["HT9425-23-1 to 0234"]}],"id":[{"id":"10.13039\/100000005","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Hoveida Family Foundation"},{"name":"Mayo Clinic Cancer Center"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,8,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Artificial intelligence (AI)\u2013based, mammography breast cancer risk prediction models show improved discriminatory accuracy relative to clinical risk models. However, data on their calibration are limited. This study compared model performance of 3 clinical breast cancer risk models: Gail, Tyrer\u2013Cuzick v8, and Breast Cancer Surveillance Consortium v3 with the MIRAI AI-risk model.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Digital mammograms were ascertained from a screening mammography cohort of 12\u200a308 women within the Mayo Clinic Biobank with 250 incident breast cancers (176 invasive) within 5 years. We predicted 5-year breast cancer risk, estimated discriminatory accuracy (C-index), and calibration (observed-to-expected ratio) of both overall and invasive breast cancer and compared estimates using bootstrapping approaches.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>MIRAI demonstrated similar or improved discriminatory accuracy of overall breast cancer (C-index\u2009=\u20090.71, 95% confidence interval [CI] = 0.68 to 0.74) and invasive breast cancer (C-index\u2009=\u20090.71, 95% CI\u2009=\u20090.67 to 0.75) compared with clinical models (overall breast cancer: C-index\u2009=\u20090.59-0.68; invasive breast cancer: C-index\u2009=\u20090.60-0.68). MIRAI\u2019s calibration for risk of overall breast cancer (observed-to-expected ratio\u2009=\u20090.96, 95% CI\u2009=\u20090.85 to 1.08) was improved compared with Gail (observed-to-expected ratio\u2009=\u20091.22, 95% CI\u2009=\u20091.07 to 1.38) and Breast Cancer Surveillance Consortium (observed-to-expected ratio =\u20091.38, 95% CI\u2009=\u20091.22 to 1.56) but similar to TC with volumetric percent density and polygenic risk score (observed-to-expected ratio\u2009=\u20090.99, 95% CI\u2009=\u20090.87 to 1.13). However, for low-risk women (approximately 50%), MIRAI overestimated risk of overall breast cancer. MIRAI also overestimated risk of invasive breast cancer across the risk spectrum (observed-to-expected ratio\u2009=\u20090.68, 95% CI\u2009=\u20090.58 to 0.78), whereas clinical models had good calibration (observed-to-expected ratio\u2009=\u20090.86\u20130.99).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>MIRAI demonstrated stronger discriminatory accuracy than clinical models for 5-year overall and invasive breast cancer risk prediction but overestimated risk for both breast cancer endpoints. AI-based risk models should consider discriminatory accuracy and calibration for invasive cancer before implementation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/jnci\/djag083","type":"journal-article","created":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T12:35:34Z","timestamp":1774355734000},"page":"1485-1495","source":"Crossref","is-referenced-by-count":3,"title":["Performance of clinical breast cancer risk prediction models vs a mammography-based artificial intelligence risk model"],"prefix":"10.1093","volume":"118","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-6040-217X","authenticated-orcid":false,"given":"Medha","family":"Kaul","sequence":"first","affiliation":[{"name":"Department of Quantitative Health Sciences, Mayo Clinic , Rochester, MN,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1340-0647","authenticated-orcid":false,"given":"Christopher G","family":"Scott","sequence":"additional","affiliation":[{"name":"Department of Quantitative Health Sciences, Mayo Clinic , Rochester, MN,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-7641-3096","authenticated-orcid":false,"given":"Alena","family":"Wadzinske","sequence":"additional","affiliation":[{"name":"Department of Quantitative Health Sciences, Mayo Clinic , Rochester, MN,","place":["United States"]},{"name":"Division of Biology and Biomedical Sciences, Washington University in St. Louis , St. Louis, MO,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3327-8004","authenticated-orcid":false,"given":"Imon","family":"Banerjee","sequence":"additional","affiliation":[{"name":"Department of Radiology, Mayo Clinic , Phoenix, AZ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dan","family":"Hursh","sequence":"additional","affiliation":[{"name":"Department of Quantitative Health Sciences, Mayo Clinic , Rochester, MN,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4208-2708","authenticated-orcid":false,"given":"Aaron","family":"Norman","sequence":"additional","affiliation":[{"name":"Department of Quantitative Health Sciences, Mayo Clinic , Rochester, MN,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fang-Fang","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Quantitative Health Sciences, Mayo Clinic , Rochester, MN,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2247-7777","authenticated-orcid":false,"given":"Ramon","family":"Correa-Medero","sequence":"additional","affiliation":[{"name":"Department of Radiology, Mayo Clinic , Phoenix, AZ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9417-9985","authenticated-orcid":false,"given":"Fergus","family":"Couch","sequence":"additional","affiliation":[{"name":"Division of Experimental Pathology and Laboratory Medicine, Department of Laboratory Medicine and Pathology, Mayo Clinic , Rochester, MN,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2235-4542","authenticated-orcid":false,"given":"Sandhya","family":"Pruthi","sequence":"additional","affiliation":[{"name":"Division of General Internal Medicine, Department of Internal Medicine, Mayo Clinic , Rochester, MN,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9031-5126","authenticated-orcid":false,"given":"Despina","family":"Kontos","sequence":"additional","affiliation":[{"name":"Department of Radiology, Columbia University Irving Medical Center , New York City, NY,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3068-2669","authenticated-orcid":false,"given":"Anne Marie","family":"McCarthy","sequence":"additional","affiliation":[{"name":"Departments of Biostatistics and Epidemiology, University of Pennsylvania Perelman School of Medicine , Philadelphia, PA,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Janet","family":"Olson","sequence":"additional","affiliation":[{"name":"Department of Quantitative Health Sciences, Mayo Clinic , Rochester, MN,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8492-9102","authenticated-orcid":false,"given":"Stacey","family":"Winham","sequence":"additional","affiliation":[{"name":"Department of Quantitative Health Sciences, Mayo Clinic , Rochester, MN,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8793-8779","authenticated-orcid":false,"given":"Karla","family":"Kerlikowske","sequence":"additional","affiliation":[{"name":"Departments of Medicine and Epidemiology and Biostatistics, University of California San Francisco , San Francisco, CA,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1962-9322","authenticated-orcid":false,"given":"Celine M","family":"Vachon","sequence":"additional","affiliation":[{"name":"Department of Quantitative Health Sciences, Mayo Clinic , Rochester, MN,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,3,26]]},"reference":[{"key":"2026081003525881800_djag083-B1","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1093\/jbi\/wbab001","article-title":"Assessing risk of breast cancer: a review of risk prediction models","volume":"3","author":"Kim","year":"2021","journal-title":"J Breast Imaging"},{"key":"2026081003525881800_djag083-B2","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1007\/s10549-016-3953-2","article-title":"Breast cancer risk prediction using a clinical risk model and polygenic risk score","volume":"159","author":"Shieh","year":"2016","journal-title":"Breast Cancer Res Treat"},{"key":"2026081003525881800_djag083-B3","doi-asserted-by":"publisher","first-page":"476","DOI":"10.1001\/jamaoncol.2017.4881","article-title":"Use of single-nucleotide polymorphisms and mammographic density plus classic risk factors for breast cancer risk prediction","volume":"4","author":"van Veen","year":"2018","journal-title":"JAMA Oncol"},{"key":"2026081003525881800_djag083-B4","doi-asserted-by":"publisher","first-page":"1485","DOI":"10.1016\/j.gim.2022.03.009","article-title":"Breast cancer risk stratification in women of screening age: incremental effects of adding mammographic density, polygenic risk, and a gene panel","volume":"24","author":"Evans","year":"2022","journal-title":"Genet Med"},{"key":"2026081003525881800_djag083-B5","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/j.breast.2023.01.003","article-title":"Polygenic risk scores and breast cancer risk prediction","volume":"67","author":"Roberts","year":"2023","journal-title":"Breast"},{"key":"2026081003525881800_djag083-B6","doi-asserted-by":"publisher","first-page":"109019","DOI":"10.1016\/j.ejrad.2020.109019","article-title":"Impact of adding breast density to breast cancer risk models: a systematic review","volume":"127","author":"Vilmun","year":"2020","journal-title":"Eur J Radiol"},{"key":"2026081003525881800_djag083-B7","doi-asserted-by":"publisher","first-page":"857","DOI":"10.1001\/jama.2019.11885","article-title":"Medication use to reduce risk of breast cancer: US preventive services task force recommendation statement","volume":"322","author":"Owens","year":"2019","journal-title":"JAMA"},{"key":"2026081003525881800_djag083-B8","doi-asserted-by":"publisher","first-page":"3152","DOI":"10.1200\/JCO.19.01472","article-title":"Use of endocrine therapy for breast cancer risk reduction: ASCO clinical practice guideline update","volume":"37","author":"Visvanathan","year":"2019","journal-title":"J Clin Oncol"},{"key":"2026081003525881800_djag083-B9","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1148\/radiol.2019182716","article-title":"A deep learning mammography-based model for improved breast cancer risk prediction","volume":"292","author":"Yala","year":"2019","journal-title":"Radiology"},{"key":"2026081003525881800_djag083-B10","doi-asserted-by":"publisher","first-page":"eaba4373","DOI":"10.1126\/scitranslmed.aba4373","article-title":"Toward robust mammography-based models for breast cancer risk","volume":"13","author":"Yala","year":"2021","journal-title":"Sci Transl Med"},{"key":"2026081003525881800_djag083-B11"},{"key":"2026081003525881800_djag083-B12","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1016\/j.jacr.2023.10.018","article-title":"Artificial intelligence-driven mammography-based future breast cancer risk prediction: a systematic review","volume":"21","author":"Schopf","year":"2024","journal-title":"J Am Coll Radiol"},{"key":"2026081003525881800_djag083-B13","doi-asserted-by":"publisher","first-page":"1732","DOI":"10.1200\/jco.21.01337","article-title":"Multi-Institutional Validation of a Mammography-Based Breast Cancer Risk Model","volume":"40","author":"Yala","year":"2022","journal-title":"J Clin Oncol"},{"key":"2026081003525881800_djag083-B14","doi-asserted-by":"publisher","first-page":"1377","DOI":"10.1001\/jama.2017.12126","article-title":"Discrimination and calibration of clinical prediction models: users\u2019 guides to the medical literature","volume":"318","author":"Alba","year":"2017","journal-title":"JAMA"},{"key":"2026081003525881800_djag083-B15","doi-asserted-by":"publisher","first-page":"994","DOI":"10.1093\/jnci\/djy013","article-title":"Breast cancer risk model requirements for counseling, prevention, and screening","volume":"110","author":"Gail","year":"2018","journal-title":"J Natl Cancer Inst"},{"key":"2026081003525881800_djag083-B16","doi-asserted-by":"publisher","first-page":"e222733","DOI":"10.1148\/radiol.222733","article-title":"Comparison of mammography AI algorithms with a clinical risk model for 5-year breast cancer risk prediction: an observational study","volume":"307","author":"Arasu","year":"2023","journal-title":"Radiology"},{"key":"2026081003525881800_djag083-B17","doi-asserted-by":"publisher","first-page":"952","DOI":"10.1016\/j.mayocp.2013.06.006","article-title":"The Mayo clinic biobank: a building block for individualized medicine","volume":"88","author":"Olson","year":"2013","journal-title":"Mayo Clin Proc"},{"key":"2026081003525881800_djag083-B18","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1016\/j.ajhg.2018.11.002","article-title":"Polygenic risk scores for prediction of breast cancer and breast cancer subtypes","volume":"104","author":"Mavaddat","year":"2019","journal-title":"Am J Human Genet"},{"key":"2026081003525881800_djag083-B19","doi-asserted-by":"publisher","first-page":"710","DOI":"10.1148\/radiol.2015151261","article-title":"Comparison of clinical and automated breast density measurements: implications for risk prediction and supplemental screening","volume":"279","author":"Brandt","year":"2016","journal-title":"Radiology"},{"key":"2026081003525881800_djag083-B20","year":"2024"},{"key":"2026081003525881800_djag083-B21","doi-asserted-by":"publisher","first-page":"1355","DOI":"10.1093\/jnci\/djac142","article-title":"Deep learning vs traditional breast cancer risk models to support risk-based mammography screening","volume":"114","author":"Lehman","year":"2022","journal-title":"J Natl Cancer Inst"},{"key":"2026081003525881800_djag083-B22","doi-asserted-by":"publisher","first-page":"2584","DOI":"10.1007\/s11606-023-08043-4","article-title":"Variability among breast cancer risk classification models when applied at the level of the individual woman","volume":"38","author":"Paige","year":"2023","journal-title":"J Gen Intern Med"},{"key":"2026081003525881800_djag083-B23","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1148\/radiol.2018180179","article-title":"Radiomic phenotypes of mammographic parenchymal complexity: toward augmenting breast density in breast cancer risk assessment","volume":"290","author":"Kontos","year":"2019","journal-title":"Radiology"},{"key":"2026081003525881800_djag083-B24","doi-asserted-by":"publisher","first-page":"e240281","DOI":"10.1148\/radiol.240281","article-title":"Radiomic parenchymal phenotypes of breast texture from mammography and association with risk of breast cancer","volume":"315","author":"Winham","year":"2025","journal-title":"Radiology"},{"key":"2026081003525881800_djag083-B25","doi-asserted-by":"publisher","first-page":"1918","DOI":"10.1001\/jama.2024.5534","article-title":"Screening for breast cancer: US preventive services task force recommendation statement","volume":"331","author":"Nicholson","year":"2024","journal-title":"JAMA"}],"container-title":["JNCI: Journal of the National Cancer Institute"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jnci\/advance-article-pdf\/doi\/10.1093\/jnci\/djag083\/67550832\/djag083.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jnci\/article-pdf\/118\/8\/1485\/67550832\/djag083.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jnci\/article-pdf\/118\/8\/1485\/67550832\/djag083.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T07:53:05Z","timestamp":1786348385000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jnci\/article\/118\/8\/1485\/8541670"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,26]]},"references-count":25,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2026,3,26]]},"published-print":{"date-parts":[[2026,8,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jnci\/djag083","relation":{},"ISSN":["0027-8874","1460-2105"],"issn-type":[{"value":"0027-8874","type":"print"},{"value":"1460-2105","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,8]]},"published":{"date-parts":[[2026,3,26]]}}}