{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T18:03:55Z","timestamp":1789495435809,"version":"build-2803163510"},"reference-count":20,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T00:00:00Z","timestamp":1789430400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"\n Purpose<\/jats:title>\n To evaluate the diagnostic performance metrics, referral patterns, and real-world implementation characteristics associated with a Breast AI\u2122-supported ultrasound assessment pathway across multiple heterogeneous healthcare settings.<\/jats:p>\n <\/jats:sec>\n \n Materials and methods<\/jats:title>\n This prospective multi-site observational study included 1,129 women undergoing routine or symptom-driven breast assessment across five healthcare facilities in South Africa between April 2023 and April 2025. Breast AI\u2122 was used as an adjunctive ultrasound-based clinical decision-support tool alongside standard clinical assessment and breast ultrasound imaging. Referral outcomes and histopathological diagnoses were recorded where clinically indicated. Diagnostic performance metrics, including sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV), were calculated using predefined dichotomised Breast AI\u2122 risk categories. Site-level comparisons were assessed using chi-square analysis.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n Among 1,129 clinical assessments, 417 patients underwent referral for further diagnostic evaluation, with 405 histopathologically confirmed malignancies identified. Referral-associated malignancy rates remained relatively consistent across participating healthcare sites, with no statistically significant site-level differences observed (\u03c7\u00b2\u2009=\u20091.67, p\u2009=\u20090.795). Diagnostic performance analysis demonstrated a sensitivity of 99.3% (95% CI: 97.8\u201399.8), specificity of 69.8% (95% CI: 66.3\u201373.1), PPV of 64.7% (95% CI: 61.2\u201368.0), and NPV of 99.4% (95% CI: 98.3\u201399.8). Higher Breast AI\u2122 risk classifications were more frequently associated with invasive ductal carcinoma and invasive lobular carcinoma, whereas approximately 30% of ductal carcinoma in situ cases were classified within the low-risk category. The median interval between Breast AI\u2122 assessment and histopathological confirmation was 18 days (IQR: 10\u201332 days).<\/jats:p>\n <\/jats:sec>\n \n Conclusion<\/jats:title>\n In this prospective observational multi-site cohort, Breast AI\u2122-supported ultrasound assessment demonstrated high observed negative predictive value and reproducible risk stratification across heterogeneous healthcare environments. However, interpretation of diagnostic accuracy metrics is limited by differential histopathological verification and the absence of long-term interval cancer follow-up among low-risk patients. The findings support the feasibility of integrating AI-supported ultrasound assessment into resource-variable clinical settings, while highlighting the need for future comparative, longitudinal, and health-economic evaluation studies<\/jats:p>\n <\/jats:sec>","DOI":"10.1371\/journal.pone.0357975","type":"journal-article","created":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T17:23:14Z","timestamp":1789492994000},"page":"e0357975","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-site observational evaluation of Breast AI\u2122-supported ultrasound risk stratification in breast cancer assessment pathways"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7602-0206","authenticated-orcid":true,"given":"Kathryn","family":"Malherbe","sequence":"first","affiliation":[{"name":"Malherbe Imaging Inc., Diagnostic Imaging","place":["Pretoria, South Africa"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carol A.","family":"Benn","sequence":"additional","affiliation":[{"name":"University of Witwatersrand","place":["Johannesburg, South Africa"],"department":["Department of Immunology"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gerhard","family":"Botha","sequence":"additional","affiliation":[{"name":"University of Pretoria","place":["Pretoria, South Africa"],"department":["Department of Family Medicine"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,9,15]]},"reference":[{"issue":"7","key":"pone.0357975.ref001","doi-asserted-by":"crossref","first-page":"2112","DOI":"10.3390\/cancers15072112","article-title":"Ultrasound for breast cancer screening in resource-limited settings: current practice and future directions","volume":"15","author":"Q Dan","year":"2023","journal-title":"Cancers (Basel)"},{"issue":"9","key":"pone.0357975.ref002","doi-asserted-by":"crossref","first-page":"916","DOI":"10.1093\/jnci\/djy222","article-title":"Stand-alone artificial intelligence for breast cancer detection in mammography: comparison with 101 radiologists","volume":"111","author":"A Rodriguez-Ruiz","year":"2019","journal-title":"J Natl Cancer Inst"},{"issue":"1","key":"pone.0357975.ref003","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1148\/radiol.2016161174","article-title":"National performance benchmarks for modern screening digital mammography: update from the breast cancer surveillance consortium","volume":"283","author":"CD Lehman","year":"2017","journal-title":"Radiology"},{"issue":"11","key":"pone.0357975.ref004","doi-asserted-by":"crossref","first-page":"1828","DOI":"10.1001\/jamainternmed.2015.5231","article-title":"Diagnostic accuracy of digital screening mammography with and without computer-aided detection","volume":"175","author":"CD Lehman","year":"2015","journal-title":"JAMA Intern Med"},{"issue":"2","key":"pone.0357975.ref005","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1148\/radiol.2018181371","article-title":"Detection of breast cancer with mammography: effect of an artificial intelligence support system","volume":"290","author":"A Rodr\u00edguez-Ruiz","year":"2019","journal-title":"Radiology"},{"issue":"10","key":"pone.0357975.ref006","article-title":"Artificial intelligence for breast cancer detection in screening mammography in Sweden: a prospective, population-based, paired-reader, non-inferiority study","volume":"5","author":"K Dembrower","year":"2023","journal-title":"Lancet Digit Health"},{"issue":"1","key":"pone.0357975.ref007","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1186\/s13089-022-00274-6","article-title":"Comparison of four handheld point-of-care ultrasound devices by expert users","volume":"14","author":"M-PT Le","year":"2022","journal-title":"Ultrasound J"},{"issue":"1","key":"pone.0357975.ref008","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1200\/JGO.2015.000430","article-title":"Breast cancer screening in low- and middle-income countries: a perspective from Malawi","volume":"2","author":"LA Gutnik","year":"2015","journal-title":"J Glob Oncol"},{"issue":"12","key":"pone.0357975.ref009","doi-asserted-by":"crossref","first-page":"1377","DOI":"10.1177\/15353702211006047","article-title":"Breast cancer in sub-Saharan Africa: the current state and uncertain future","volume":"246","author":"CA Anyigba","year":"2021","journal-title":"Exp Biol Med (Maywood)"},{"issue":"1","key":"pone.0357975.ref010","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1111\/tbj.12357","article-title":"Breast cancer in low- and middle-income countries (LMICs): a shifting tide in global health","volume":"21","author":"BO Anderson","year":"2015","journal-title":"Breast J"},{"issue":"3","key":"pone.0357975.ref011","doi-asserted-by":"crossref","first-page":"262","DOI":"10.3390\/bioengineering11030262","article-title":"Evaluating the role of breast ultrasound in early detection of breast cancer in low- and middle-income countries: a comprehensive narrative review","volume":"11","author":"R Iacob","year":"2024","journal-title":"Bioengineering (Basel)"},{"issue":"5","key":"pone.0357975.ref012","doi-asserted-by":"crossref","DOI":"10.1093\/jnci\/djw290","article-title":"Breast cancer screening in the precision medicine era: risk-based screening in a population-based trial","volume":"109","author":"Y Shieh","year":"2017","journal-title":"J Natl Cancer Inst"},{"issue":"16","key":"pone.0357975.ref013","doi-asserted-by":"crossref","first-page":"1224","DOI":"10.1093\/jnci\/djq239","article-title":"Breast tissue composition and susceptibility to breast cancer","volume":"102","author":"NF Boyd","year":"2010","journal-title":"J Natl Cancer Inst"},{"issue":"3","key":"pone.0357975.ref014","doi-asserted-by":"crossref","first-page":"310","DOI":"10.6004\/jnccn.2018.0012","article-title":"Breast cancer, version 4.2017, NCCN clinical practice guidelines in oncology","volume":"16","author":"WJ Gradishar","year":"2018","journal-title":"J Natl Compr Canc Netw"},{"key":"pone.0357975.ref015","unstructured":"Cancer Association of South Africa (CANSA). Breast cancer. Available from: https:\/\/cansa.org.za\/breast-cancer\/. 2024. Accessed 2026 May 15."},{"key":"pone.0357975.ref016","author":"K Malherbe","year":"2021","journal-title":"Diagnostic algorithm for accurate detection of breast carcinoma on ultrasound [dissertation]."},{"issue":"1","key":"pone.0357975.ref017","first-page":"2772","article-title":"An audit of breast cancer in patients 40 years and younger in two Johannesburg academic hospitals","volume":"28","author":"N Chaane","year":"2024","journal-title":"SA J Radiol"},{"issue":"1","key":"pone.0357975.ref018","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s40487-023-00248-1","article-title":"From incidence to intervention: a comprehensive look at breast cancer in South Africa","volume":"12","author":"Z Dlamini","year":"2024","journal-title":"Oncol Ther"},{"issue":"22","key":"pone.0357975.ref019","doi-asserted-by":"crossref","first-page":"2987","DOI":"10.1002\/(SICI)1097-0258(19991130)18:22<2987::AID-SIM205>3.0.CO;2-B","article-title":"Using a combination of reference tests to assess the accuracy of a new diagnostic test","volume":"18","author":"TA Alonzo","year":"1999","journal-title":"Stat Med"},{"issue":"1","key":"pone.0357975.ref020","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1007\/s00330-020-07148-2","article-title":"Challenges and solutions for introducing artificial intelligence (AI) in daily clinical workflow","volume":"31","author":"E Kotter","year":"2021","journal-title":"Eur Radiol"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0357975","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T17:23:20Z","timestamp":1789493000000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0357975"}},"subtitle":[],"editor":[{"given":"Elingarami","family":"Sauli","sequence":"first","affiliation":[{"name":"Nelson Mandela African Institute of Science and Technology","place":["UNITED REPUBLIC OF TANZANIA"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,9,15]]},"references-count":20,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9,15]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0357975","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,15]]}}}