{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T10:48:53Z","timestamp":1782730133999,"version":"3.54.5"},"reference-count":40,"publisher":"Scientific Scholar","content-domain":{"domain":["clinicalimagingscience.org"],"crossmark-restriction":true},"short-container-title":["JCIS"],"abstract":"\n Objectives:<\/jats:title>\n Triple-negative breast cancer (TNBC) is an aggressive subtype of breast cancer lacking estrogen receptor, progesterone receptor, and human epidermal growth factor R expression. This study aimed to identify ultrasound features associated with TNBC and construct a robust diagnostic model using machine learning techniques.<\/jats:p>\n <\/jats:sec>\n \n Material and Methods:<\/jats:title>\n A total of 433 BC patients (47 TNBC and 386 non-TNBC) with complete clinical and ultrasound data were retrospectively analyzed. Univariate and multivariate logistic regression analyses identified independent ultrasound predictors of TNBC. Subsequently, 108 combinations of feature selection methods and machine learning classifiers were systematically evaluated to identify the optimal diagnostic model. Model performance was assessed using receiver operating characteristic curves, decision curve analysis (DCA), and calibration plots in both training and validation cohorts. The ethical approval was obtained from the institutional review board, and the requirement for individual written informed consent was waived due to the retrospective nature of the study.<\/jats:p>\n <\/jats:sec>\n \n Results:<\/jats:title>\n \n Multivariate analysis identified posterior acho, margins, calcification, and aspect ratio as independent predictors of TNBC (\n p<\/jats:italic>\n < 0.05). Among all model combinations, the Stepwise Generalized Linear Model combined with Random Forest model achieved the best performance, with an area under the curve (AUC) of 1.000 in the training set and 0.913 in the validation set. Subgroup analysis revealed higher model accuracy in patients aged \u226450 years (AUC = 0.911) compared to those >50 years (AUC = 0.706). DCA and calibration plots indicated high clinical utility and excellent calibration performance.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusion:<\/jats:title>\n Specific ultrasound features can effectively distinguish TNBC from non-TNBC. A machine learning-based diagnostic model that integrates multiple algorithmic combinations demonstrates strong generalizability and may serve as a valuable clinical tool, particularly for younger patients.<\/jats:p>\n <\/jats:sec>","DOI":"10.25259\/jcis_283_2025","type":"journal-article","created":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T10:38:38Z","timestamp":1782729518000},"page":"25","update-policy":"https:\/\/doi.org\/10.25259\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Construction of an ultrasound feature-based diagnostic model for predicting triple-negative breast cancer using 108 machine learning algorithm combinations"],"prefix":"10.25259","volume":"16","author":[{"given":"Xin","family":"Zhang","sequence":"first","affiliation":[{"name":"Department of Ultrasound, Ningxia Medical University General Hospital, Yinchuan, China,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaomin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Ultrasound, Ningxia Medical University General Hospital, Yinchuan, China,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shan","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Ultrasound, Ningxia Medical University General Hospital, Yinchuan, China,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ningxia","family":"Ao","sequence":"additional","affiliation":[{"name":"Department of Ultrasound, Ningxia Medical University General Hospital, Yinchuan, China,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yali","family":"Cao","sequence":"additional","affiliation":[{"name":"Department of Ultrasound, Ningxia Medical University General Hospital, Yinchuan, China,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangfei","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Ultrasound, Ningxia Medical University General Hospital, Yinchuan, China,"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10894","published-online":{"date-parts":[[2026,6,29]]},"reference":[{"key":"10.25259\/JCIS_283_2025\/ref-1","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1038\/s41523-022-00468-0","article-title":"Triple negative breast cancer: Pitfalls and progress","volume":"8","author":"Zagami","year":"2022","journal-title":"NPJ Breast Cancer"},{"key":"10.25259\/JCIS_283_2025\/ref-2","doi-asserted-by":"publisher","first-page":"836417","DOI":"10.3389\/fmolb.2022.836417","article-title":"Triple-negative breast cancer: A brief review about epidemiology, risk factors, signaling pathways, treatment and role of artificial intelligence","volume":"9","author":"Almansour","year":"2022","journal-title":"Front Mol Biosci"},{"key":"10.25259\/JCIS_283_2025\/ref-3","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1186\/s43556-022-00071-6","article-title":"Therapeutic progress and challenges for triple negative breast cancer: Targeted therapy and immunotherapy","volume":"3","author":"Yang","year":"2022","journal-title":"Mol Biomed"},{"key":"10.25259\/JCIS_283_2025\/ref-4","doi-asserted-by":"publisher","first-page":"1405491","DOI":"10.3389\/fonc.2024.1405491","article-title":"Advancements and challenges in triple-negative breast cancer: a comprehensive review of therapeutic and diagnostic strategies","volume":"14","author":"Xiong","year":"2024","journal-title":"Front Oncol"},{"key":"10.25259\/JCIS_283_2025\/ref-5","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1038\/s41392-024-02108-4","article-title":"Breast cancer: Pathogenesis and treatments","volume":"10","author":"Xiong","year":"2025","journal-title":"Signal Transduct Target Ther"},{"key":"10.25259\/JCIS_283_2025\/ref-6","doi-asserted-by":"publisher","first-page":"981","DOI":"10.20892\/j.issn.2095-3941.2023.0294","article-title":"Hot issues in triple-negative breast cancer","volume":"20","author":"Hao","year":"2024","journal-title":"Cancer Biol Med"},{"key":"10.25259\/JCIS_283_2025\/ref-7","doi-asserted-by":"publisher","first-page":"1465511","DOI":"10.3389\/fonc.2025.1465511","article-title":"Improvement in breast cancer survival across molecular subtypes in Hungary between 2011 and 2020: A nationwide, retrospective study","volume":"15","author":"Darida","year":"2025","journal-title":"Front Oncol"},{"key":"10.25259\/JCIS_283_2025\/ref-8","doi-asserted-by":"publisher","first-page":"1796","DOI":"10.3390\/pharmaceutics15071796","article-title":"Triple negative breast cancer treatment options and limitations: Future outlook","volume":"15","author":"Obidiro","year":"2023","journal-title":"Pharmaceutics"},{"key":"10.25259\/JCIS_283_2025\/ref-9","doi-asserted-by":"publisher","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":"Iacob","year":"2024","journal-title":"Bioengineering (Basel)"},{"key":"10.25259\/JCIS_283_2025\/ref-10","doi-asserted-by":"publisher","first-page":"e59054","DOI":"10.7759\/cureus.59054","article-title":"Comparative effectiveness of mammography, ultrasound, and MRI in the detection of breast carcinoma in dense breast tissue: A systematic review","volume":"16","author":"Abu Abeelh","year":"2024","journal-title":"Cureus"},{"key":"10.25259\/JCIS_283_2025\/ref-11","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1055\/s-0040-1722156","article-title":"Comparison of automated breast ultrasound and hand-held breast ultrasound in the screening of dense breasts","volume":"43","author":"Philadelpho","year":"2021","journal-title":"Rev Bras Ginecol Obstet"},{"key":"10.25259\/JCIS_283_2025\/ref-12","doi-asserted-by":"publisher","first-page":"886","DOI":"10.1186\/s12885-025-14233-6","article-title":"Prediction models of breast cancer molecular subtypes based on multimodal ultrasound and clinical features","volume":"25","author":"Li","year":"2025","journal-title":"BMC Cancer"},{"key":"10.25259\/JCIS_283_2025\/ref-13","doi-asserted-by":"publisher","first-page":"1604","DOI":"10.1016\/j.acra.2016.05.017","article-title":"A review of supplemental screening ultrasound for breast cancer: Certain populations of women with dense breast tissue may benefit","volume":"23","author":"Burkett","year":"2016","journal-title":"Acad Radiol"},{"key":"10.25259\/JCIS_283_2025\/ref-14","doi-asserted-by":"publisher","first-page":"61","DOI":"10.3390\/jpm11020061","article-title":"Breast cancer type classification using machine learning","volume":"11","author":"Wu","year":"2021","journal-title":"J Pers Med"},{"key":"10.25259\/JCIS_283_2025\/ref-15","doi-asserted-by":"publisher","first-page":"1652","DOI":"10.1007\/s00330-021-08271-4","article-title":"Predicting the molecular subtype of breast cancer and identifying interpretable imaging features using machine learning algorithms","volume":"32","author":"Ma","year":"2022","journal-title":"Eur Radiol"},{"key":"10.25259\/JCIS_283_2025\/ref-16","doi-asserted-by":"publisher","first-page":"59","DOI":"10.3233\/BD-220018","article-title":"Machine learning analysis of breast ultrasound to classify triple negative and HER2+ breast cancer subtypes","volume":"42","author":"Ferre","year":"2023","journal-title":"Breast Dis"},{"key":"10.25259\/JCIS_283_2025\/ref-17","doi-asserted-by":"publisher","first-page":"100694","DOI":"10.1016\/j.xcrm.2022.100694","article-title":"Radiogenomic analysis reveals tumor heterogeneity of triple-negative breast cancer","volume":"3","author":"Jiang","year":"2022","journal-title":"Cell Rep Med"},{"key":"10.25259\/JCIS_283_2025\/ref-18","first-page":"152","article-title":"Association of machine learning ultrasound radiomics and disease outcome in triple negative breast cancer","volume":"12","author":"Wang","year":"2022","journal-title":"Am J Cancer Res"},{"key":"10.25259\/JCIS_283_2025\/ref-19","doi-asserted-by":"publisher","first-page":"1158736","DOI":"10.3389\/fonc.2023.1158736","article-title":"Conventional ultrasound and contrast-enhanced ultrasound radiomics in breast cancer and molecular subtype diagnosis","volume":"13","author":"Gong","year":"2023","journal-title":"Front Oncol"},{"key":"10.25259\/JCIS_283_2025\/ref-20","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1007\/s11517-022-02728-4","article-title":"Deep learning-based system for automatic prediction of triple-negative breast cancer from ultrasound images","volume":"61","author":"Boulenger","year":"2023","journal-title":"Med Biol Eng Comput"},{"key":"10.25259\/JCIS_283_2025\/ref-21","doi-asserted-by":"publisher","first-page":"e085340","DOI":"10.1136\/bmjopen-2024-085340","article-title":"Ultrasound-based comparative analysis and nomogram development for predicting triple-negative and non-triple-negative breast cancer: A 4-year institutional study in Quanzhou first hospital","volume":"14","author":"Su","year":"2024","journal-title":"BMJ Open"},{"key":"10.25259\/JCIS_283_2025\/ref-22","doi-asserted-by":"publisher","first-page":"i23","DOI":"10.1093\/annonc\/mds191","article-title":"Imaging of triple-negative breast cancer","volume":"23","author":"Dogan","year":"2012","journal-title":"Ann Oncol"},{"key":"10.25259\/JCIS_283_2025\/ref-23","first-page":"AT10343","article-title":"Predictive value of lump aspect ratio, boundary clarity, and spiculation\/angularity in distinguishing benign and malignant breast lumps","author":"Gao","year":"2024","journal-title":"Altern Ther Health Med"},{"key":"10.25259\/JCIS_283_2025\/ref-24","doi-asserted-by":"publisher","first-page":"9040","DOI":"10.1038\/s41598-018-27222-6","article-title":"Triple-negative invasive breast carcinoma: The association between the sonographic appearances with clinicopathological feature","volume":"8","author":"Li","year":"2018","journal-title":"Sci Rep"},{"key":"10.25259\/JCIS_283_2025\/ref-25","doi-asserted-by":"publisher","first-page":"6173","DOI":"10.1002\/cam4.3305","article-title":"Association of sonographic features and molecular subtypes in predicting breast cancer disease outcomes","volume":"9","author":"Wang","year":"2020","journal-title":"Cancer Med"},{"key":"10.25259\/JCIS_283_2025\/ref-26","doi-asserted-by":"publisher","first-page":"2590647","DOI":"10.1155\/2022\/2590647","article-title":"Clinical value of preoperative ultrasound signs in evaluating axillary lymph node status in triple-negative breast cancer","volume":"2022","author":"Wang","year":"2022","journal-title":"J Oncol"},{"key":"10.25259\/JCIS_283_2025\/ref-27","doi-asserted-by":"publisher","first-page":"5987","DOI":"10.62347\/VTEW9920","article-title":"Prediction of axillary lymph node metastasis in breast cancer using an ultrasonic feature-and clinical databased model","volume":"14","author":"Jin","year":"2024","journal-title":"Am J Cancer Res"},{"key":"10.25259\/JCIS_283_2025\/ref-28","doi-asserted-by":"publisher","first-page":"5394","DOI":"10.3390\/jcm10225394","article-title":"Is there a correlation between multiparametric assessment in ultrasound and intrinsic subtype of breast cancer?","volume":"10","author":"Gumowska","year":"2021","journal-title":"J Clin Med"},{"key":"10.25259\/JCIS_283_2025\/ref-29","doi-asserted-by":"publisher","first-page":"9336185","DOI":"10.1155\/2022\/9336185","article-title":"Calcification, posterior acoustic, and blood flow: Ultrasonic characteristics of triple-negative breast cancer","volume":"2022","author":"Wang","year":"2022","journal-title":"J Healthc Eng"},{"key":"10.25259\/JCIS_283_2025\/ref-30","doi-asserted-by":"publisher","first-page":"2125","DOI":"10.21873\/anticanres.14171","article-title":"Clinical imaging of the heterogeneous group of triple-negative breast cancer","volume":"40","author":"M\u00fcller","year":"2020","journal-title":"Anticancer Res"},{"key":"10.25259\/JCIS_283_2025\/ref-31","doi-asserted-by":"publisher","first-page":"448","DOI":"10.5152\/dir.2015.14515","article-title":"The role of ultrasonographic findings to predict molecular subtype, histologic grade, and hormone receptor status of breast cancer","volume":"21","author":"\u00c7elebi","year":"2015","journal-title":"Diagn Interv Radiol"},{"key":"10.25259\/JCIS_283_2025\/ref-32","doi-asserted-by":"publisher","first-page":"889","DOI":"10.1177\/0284185113488580","article-title":"Mammographic and ultrasonographic features of triple-negative breast cancer: A comparison with other breast cancer subtypes","volume":"54","author":"Kim","year":"2013","journal-title":"Acta Radiol"},{"key":"10.25259\/JCIS_283_2025\/ref-33","doi-asserted-by":"publisher","first-page":"2443041","DOI":"10.1080\/07853890.2024.2443041","article-title":"Correlation between ultrasonography and elastography parameters and molecular subtypes of breast cancer in young women","volume":"57","author":"Men","year":"2025","journal-title":"Ann Med"},{"key":"10.25259\/JCIS_283_2025\/ref-34","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.clinimag.2021.03.039","article-title":"Molecular markers, pathology, and ultrasound features of invasive breast cancer","volume":"79","author":"Huang","year":"2021","journal-title":"Clin Imaging"},{"key":"10.25259\/JCIS_283_2025\/ref-35","doi-asserted-by":"publisher","first-page":"1980","DOI":"10.21037\/gs-21-320","article-title":"Application value of conventional ultrasound combined with shear wave elastography in diagnosing triple negative breast cancer","volume":"10","author":"Sheng","year":"2021","journal-title":"Gland Surg"},{"key":"10.25259\/JCIS_283_2025\/ref-36","doi-asserted-by":"publisher","first-page":"1124","DOI":"10.1016\/j.ultrasmedbio.2018.01.013","article-title":"Clinicopathological and ultrasonic features of triple-negative breast cancers: A comparison with hormone receptor-positive\/ human epidermal growth factor receptor-2-negative breast cancers","volume":"44","author":"Wang","year":"2018","journal-title":"Ultrasound Med Biol"},{"key":"10.25259\/JCIS_283_2025\/ref-37","doi-asserted-by":"publisher","first-page":"377","DOI":"10.4021\/wjon738w","article-title":"TNBC vs non-TNBC: A retrospective review of differences in mean age, family history, smoking history, and stage at diagnosis","volume":"12","author":"Tariq","year":"2014","journal-title":"Clin Adv Hematol Oncol"},{"key":"10.25259\/JCIS_283_2025\/ref-38","doi-asserted-by":"publisher","first-page":"241","DOI":"10.4021\/wjon738w","article-title":"TNBC vs. Non-TNBC: A five-year retrospective review of differences in mean age, family history, smoking history and stage at diagnosis at an inner city university program","volume":"4","author":"Tariq","year":"2013","journal-title":"World J Oncol"},{"key":"10.25259\/JCIS_283_2025\/ref-39","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1093\/jbi\/wbae085","article-title":"Triple-negative breast cancer: Radiologic-pathologic correlation","volume":"7","author":"Valluri","year":"2025","journal-title":"J Breast Imaging"},{"key":"10.25259\/JCIS_283_2025\/ref-40","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1016\/j.clinimag.2022.09.006","article-title":"Breast cancer diagnosis in Inner-City African American and Hispanic women: The importance of early screening","volume":"92","author":"Zhang","year":"2022","journal-title":"Clin Imaging"}],"container-title":["Journal of Clinical Imaging Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/clinicalimagingscience.org\/construction-of-an-ultrasound-feature-based-diagnostic-model-for-predicting-triple-negative-breast-cancer-using-108-machine-learning-algorithm-combinations\/","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/clinicalimagingscience.org\/construction-of-an-ultrasound-feature-based-diagnostic-model-for-predicting-triple-negative-breast-cancer-using-108-machine-learning-algorithm-combinations\/","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T10:38:39Z","timestamp":1782729519000},"score":1,"resource":{"primary":{"URL":"https:\/\/clinicalimagingscience.org\/construction-of-an-ultrasound-feature-based-diagnostic-model-for-predicting-triple-negative-breast-cancer-using-108-machine-learning-algorithm-combinations\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,29]]},"references-count":40,"alternative-id":["10.25259\/JCIS_283_2025"],"URL":"https:\/\/doi.org\/10.25259\/jcis_283_2025","relation":{},"ISSN":["2156-5597","2156-7514"],"issn-type":[{"value":"2156-5597","type":"electronic"},{"value":"2156-7514","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6,29]]},"article-number":"25"}}