{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T18:14:51Z","timestamp":1777486491195,"version":"3.51.4"},"reference-count":38,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T00:00:00Z","timestamp":1773360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Oncol."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Invasive ductal carcinoma (IDC), the predominant histopathological subtype comprising about 80% of breast malignancies, continues to pose a significant clinical challenge due to frequent recurrence. Existing relapse prediction models remain limited in accuracy and generalizability. This study aimed to construct and validate machine learning\u2013based models for predicting 5-year (short- to medium term) recurrence and metastasis risk in IDC, based on recurrence-free survival (RFS) analysis.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A total of 640 IDC cases diagnosed between January 2017 and December 2019 were enrolled, data were partitioned into three sets: the training set (n = 303) from Fudan University Shanghai Cancer Center; the validation set (n = 217) from Shaoxing Central Hospital; and the test set (n = 120) from Zhejiang Cancer Hospital. Independent prognostic factors were identified through univariate and multivariate Cox regression analyses. Three predictive strategies were implemented: evaluating recurrence risk, distinguishing local from distant recurrence, and identifying metastatic sites. Light Gradient Boosting Machine (LGBM), XGBoost (XGB), Random Forest (RF), k-Nearest Neighbor (KNN), Neural Network (NN), and Support Vector Machine (SVM) were trained and validated.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The median follow-up duration was 5.7 years. Multivariate Cox regression analyses identified multiple factors significantly associated with RFS, including the rad-score, Ki-67 index, lymph node metastasis, tumor histological grade, and breast cancer family history in first- or second-degree relatives (all\n                      <jats:italic>p<\/jats:italic>\n                      &amp;lt; 0.05). In contrast, age, menopausal status, and molecular subtype showed no significant association with recurrence risk in this cohort (\n                      <jats:italic>p =<\/jats:italic>\n                      0.987,\n                      <jats:italic>p =<\/jats:italic>\n                      0.987, and\n                      <jats:italic>p =<\/jats:italic>\n                      0.960, respectively). The clinical-radiomic nomogram demonstrated strong in predictive IDC recurrence. The XGBoost model demonstrated robust and consistent predictive performance across all cohorts, achieving AUCs of 0.842, 0.848, and 0.912 on the training, validation, and test sets, respectively. On the independent test set, the model attained an accuracy of 93.8%, sensitivity of 96.3%, and specificity of 79.6%.Furthermore, density plots of the radiomic score and Ki-67 index effectively differentiated between local recurrence, bone metastasis, and metastases to other organs. Patients with lymph node metastasis and high histological grade demonstrated a higher frequency of metastases to distant organs, accounting for most cases and emphasizing the contrast with local recurrence and bone metastasis. Patients with a breast cancer family history displayed a distinct pattern of bone metastasis.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This study underscores the utility of machine learning models in forecasting recurrence and metastatic behavior in IDC. The clinical-radiomic nomograms proved valuable for individualized surgical and therapeutic decision-making in IDC patients.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2026.1734379","type":"journal-article","created":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T05:25:30Z","timestamp":1773379530000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Exploring the recurrence and metastasis of breast invasive ductal carcinoma based on machine learning and survival analysis"],"prefix":"10.3389","volume":"16","author":[{"given":"Aqiao","family":"Xu","sequence":"first","affiliation":[{"name":"Department of Radiology, The Central Hospital Affiliatedo Shaoxing University (Shaoxing Central Hospital)","place":["Shaoxing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaobo","family":"Weng","sequence":"additional","affiliation":[{"name":"Department of Radiology, The Central Hospital Affiliatedo Shaoxing University (Shaoxing Central Hospital)","place":["Shaoxing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jing","family":"Zheng","sequence":"additional","affiliation":[{"name":"Department of Radiology, The Central Hospital Affiliatedo Shaoxing University (Shaoxing Central Hospital)","place":["Shaoxing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qian","family":"Cui","sequence":"additional","affiliation":[{"name":"Department of Radiology, The Central Hospital Affiliatedo Shaoxing University (Shaoxing Central Hospital)","place":["Shaoxing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gaoyan","family":"He","sequence":"additional","affiliation":[{"name":"Department of Radiology, Shaoxing Maternity and Child Health Care Hospital","place":["Shaoxing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongran","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Public Health, Hangzhou Medical College","place":["Hangzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haitao","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Radiology, Cancer Hospital of the University of Chinese Academy of Sciences (Zhejiang Cancer Hospital)","place":["Hangzhou, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingzhu","family":"Wei","sequence":"additional","affiliation":[{"name":"Department of Radiology, Shaoxing People\u2019s Hospital (Zhejiang University Shaoxing Hospital)","place":["Shaoxing, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shengjian","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Radiology, Fudan University Shanghai Cancer Center","place":["Shanghai, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,3,13]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21834","article-title":"Global cancer statistics 2022: globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"74","author":"Bray","year":"2024","journal-title":"CA Cancer J Clin"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1016\/j.esmoop.2022.100502","article-title":"An immunological signature to predict outcome in patients with triple-negative breast cancer with residual disease after neoadjuvant chemotherapy","volume":"7","author":"Blaye","year":"2022","journal-title":"ESMO Open"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1016\/j.annonc.2023.11.016","article-title":"Early breast cancer: esmo clinical practice guideline for diagnosis, treatment and follow-up","volume":"35","author":"Loibl","year":"2024","journal-title":"Ann Oncol"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1002\/cam4.5626","article-title":"Multifocal\/multicentric breast cancer: does each focus matter","volume":"12","author":"Tong","year":"2023","journal-title":"Cancer Med"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1177\/17588359241249578","article-title":"Assessment of the impact of residual tumors at different sites post-neoadjuvant chemotherapy on prognosis in breast cancer patients and development of a disease-free survival prediction model","volume":"16","author":"Yang","year":"2024","journal-title":"Ther Adv Med Oncol"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1016\/j.esmoop.2024.103990","article-title":"Collagen signature adds prognostically significant information to staging for breast cancer","volume":"9","author":"Li","year":"2024","journal-title":"ESMO Open"},{"key":"B7","doi-asserted-by":"publisher","first-page":"e2225485","DOI":"10.1001\/jamanetworkopen.2022.25485","article-title":"Racial differences in patient-reported symptoms and adherence to adjuvant endocrine therapy among women with early-stage, hormone receptor-positive breast cancer","volume":"5","author":"Hu","year":"2022","journal-title":"JAMA Netw Open"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-024-11128-1","article-title":"Misdiagnosis in breast imaging: A statement paper from european society breast imaging (Eusobi)-part 1: the role of common errors in radiology in missed breast cancer and implications of misdiagnosis","volume":"35","author":"Thomassin-Naggara","year":"2025","journal-title":"Eur Radiol"},{"key":"B9","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1186\/s12885-022-09333-6","article-title":"New method for determining breast cancer recurrence-free survival using routinely collected real-world health data","volume":"22","author":"Jung","year":"2022","journal-title":"BMC Cancer"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-022-08910-4","article-title":"Survival outcome assessment for triple-negative breast cancer: A nomogram analysis based on integrated clinicopathological, sonographic, and mammographic characteristics","volume":"32","author":"Sheng","year":"2022","journal-title":"Eur Radiol"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1016\/j.xcrm.2024.101924","article-title":"Multimodal integration using a machine learning approach facilitates risk stratification in hr+\/her2- breast cancer","volume":"6","author":"Zhang","year":"2025","journal-title":"Cell Rep Med"},{"key":"B12","doi-asserted-by":"publisher","first-page":"2718","DOI":"10.3390\/diagnostics15212718","article-title":"From innovation to application: can emerging imaging techniques transform breast cancer diagnosis","volume":"15","author":"Hsu","year":"2025","journal-title":"Diagnostics (Basel)"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.3390\/bioengineering11111060","article-title":"Systematic meta-analysis of computer-aided detection of breast cancer using hyperspectral imaging","volume":"11","author":"Leung","year":"2024","journal-title":"Bioengineering (Basel)"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btm344","article-title":"A review of feature selection techniques in bioinformatics","volume":"23","author":"Saeys","year":"2007","journal-title":"Bioinformatics"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v033.i01","article-title":"Regularization paths for generalized linear models via coordinate descent","volume":"33","author":"Friedman","year":"2010","journal-title":"J Stat Softw"},{"key":"B16","doi-asserted-by":"publisher","first-page":"872","DOI":"10.1186\/s12885-022-09967-6","article-title":"Development and validation of a clinicoradiomic nomogram to assess the her2 status of patients with invasive ductal carcinoma","volume":"22","author":"Xu","year":"2022","journal-title":"BMC Cancer"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1016\/j.xcrm.2024.101719","article-title":"Radiomics in breast cancer: current advances and future directions","volume":"5","author":"Qi","year":"2024","journal-title":"Cell Rep Med"},{"key":"B18","doi-asserted-by":"publisher","first-page":"3728","DOI":"10.1038\/s41598-025-87622-3","article-title":"Leveraging survival analysis and machine learning for accurate prediction of breast cancer recurrence and metastasis","volume":"15","author":"Noman","year":"2025","journal-title":"Sci Rep"},{"key":"B19","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1186\/s42492-023-00147-2","article-title":"Application and prospects of ai-based radiomics in ultrasound diagnosis","volume":"6","author":"Zhang","year":"2023","journal-title":"Vis Comput Ind BioMed Art"},{"key":"B20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.diii.2022.11.004","article-title":"Artificial intelligence in diagnostic and interventional radiology: where are we now","volume":"104","author":"Boeken","year":"2023","journal-title":"Diagn Interv Imaging"},{"key":"B21","doi-asserted-by":"publisher","first-page":"187","DOI":"10.2147\/bctt.S488200","article-title":"Radiomics integration of mammography and dce-mri for predicting molecular subtypes in breast cancer patients","volume":"17","author":"Yang","year":"2025","journal-title":"Breast Cancer (Dove Med Press)"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1007\/s00432-023-05329-2","article-title":"Combining radiomics and deep learning features of intra-tumoral and peri-tumoral regions for the classification of breast cancer lung metastasis and primary lung cancer with low-dose ct","volume":"149","author":"Li","year":"2023","journal-title":"J Cancer Res Clin Oncol"},{"key":"B23","doi-asserted-by":"publisher","first-page":"e93","DOI":"10.1016\/j.acra.2020.03.004","article-title":"Association between the size and 3d ct-based radiomic features of breast cancer hepatic metastasis","volume":"28","author":"Velichko","year":"2021","journal-title":"Acad Radiol"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1155\/2024\/2540356","article-title":"Significance of estrogen\/progesterone receptor expression in metaplastic breast carcinoma","volume":"2024","author":"Hashmi","year":"2024","journal-title":"Dis Markers"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1007\/s00428-023-03645-z","article-title":"Utility of wnt family member 9b (Wnt9b) immunohistochemistry in the cytologic diagnosis of metastatic breast carcinoma","volume":"485","author":"Baykara","year":"2024","journal-title":"Virchows Arch"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.21037\/apm-21-438","article-title":"Factors associated with bone metastasis in breast cancer: A systematic review and meta-analysis","volume":"10","author":"Liu","year":"2021","journal-title":"Ann Palliat Med"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1007\/s00330-021-08146-8","article-title":"Radiomic machine learning for predicting prognostic biomarkers and molecular subtypes of breast cancer using tumor heterogeneity and angiogenesis properties on mri","volume":"32","author":"Lee","year":"2022","journal-title":"Eur Radiol"},{"key":"B28","doi-asserted-by":"publisher","first-page":"6013","DOI":"10.3390\/cancers13236013","article-title":"Machine learning models that integrate tumor texture and perfusion characteristics using low-dose breast computed tomography are promising for predicting histological biomarkers and treatment failure in breast cancer patients","volume":"13","author":"Park","year":"2021","journal-title":"Cancers (Basel)"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1007\/s10334-025-01285-9","article-title":"Mri-based texture analysis for breast cancer subtype classification in a multi-ethnic population","volume":"39","author":"Ab Mumin","year":"2025","journal-title":"Magma"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.21037\/gs-21-537","article-title":"A pre-operative mri-based brain metastasis risk-prediction model for triple-negative breast cancer","volume":"10","author":"Cheng","year":"2021","journal-title":"Gland Surg"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/6126061","article-title":"Prediction for distant metastasis of breast cancer using dynamic contrast-enhanced magnetic resonance imaging images under deep learning","volume":"2022","author":"Li","year":"2022","journal-title":"Comput Intell Neurosci"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbo.2025.100686","article-title":"Single photon emission computed tomography\/X-ray computed tomography-based radiomics analysis for diagnosis of bone metastases in patients with breast cancer","volume":"52","author":"Su","year":"2025","journal-title":"J Bone Oncol"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1093\/mam\/ozae057","article-title":"Bridging histopathology and radiomics toward prognosis of metastasis in early breast cancer","volume":"30","author":"Radulovi\u0107","year":"2024","journal-title":"Microsc Microanal"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1177\/03000605231164004","article-title":"Clinical factors affecting the long-term survival of breast cancer patients","volume":"51","author":"Li","year":"2023","journal-title":"J Int Med Res"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1093\/jnci\/djab202","article-title":"The incidence of breast cancer recurrence 10\u201332 years after primary diagnosis","volume":"114","author":"Pedersen","year":"2022","journal-title":"J Natl Cancer Inst"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1007\/s10549-017-4636-3","article-title":"20-year risk of breast cancer recurrence","volume":"168","author":"Kostev","year":"2018","journal-title":"Breast Cancer Res Treat"},{"key":"B37","doi-asserted-by":"publisher","first-page":"e70903","DOI":"10.1002\/cam4.70903","article-title":"Retrospective case-cohort study on risk factors for developing distant metastases in women with breast cancer","volume":"14","author":"Bertozzi","year":"2025","journal-title":"Cancer Med"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1001\/jamaoncol.2019.1856","article-title":"Assessment of long-term distant recurrence-free survival associated with tamoxifen therapy in postmenopausal patients with luminal a or luminal B breast cancer","volume":"5","author":"Yu","year":"2019","journal-title":"JAMA Oncol"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1734379\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T05:25:31Z","timestamp":1773379531000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1734379\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,13]]},"references-count":38,"alternative-id":["10.3389\/fonc.2026.1734379"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2026.1734379","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,13]]},"article-number":"1734379"}}