{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T06:00:27Z","timestamp":1785218427400,"version":"3.55.0"},"reference-count":39,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T00:00:00Z","timestamp":1785196800000},"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>To investigate prognostic factors for breast cancer recurrence and metastasis, and to systematically compare multiple machine learning models to develop an optimal predictive tool.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We retrospectively analyzed data from 1,056 breast cancer patients diagnosed between January 2012 and June 2021 at a single center. Patients were randomly divided into a training (n=740) and a validation (n=316) set. Univariate and multivariate Cox proportional hazards regression analyses were performed to identify independent prognostic factors. Seven machine learning algorithms (Cox regression, LASSO, Elastic-Net, Decision Tree, Random Forest, XGBoost, and GBM) were employed. All models were implemented using survival-specific adaptations. A rigorous 5-fold cross-validation framework was used for model training and hyperparameter tuning. Model performance was evaluated using time-dependent Area Under the Curve (AUC), Brier scores, calibration curves, calibration-in-the-large, calibration slopes, and Decision Curve Analysis (DCA). SHAP values were employed for model interpretation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Multivariate Cox regression revealed that tumor size (cm) (HR\u00a0=\u00a01.025, 95%CI: 1.013-1.037), lymph node dissection (HR\u00a0=\u00a00.278, 95%CI: 0.199-0.389), ER% (HR\u00a0=\u00a01.006, 95%CI: 1.003-1.009), PR% (HR\u00a0=\u00a01.005, 95%CI: 1.002-1.008), Ki-67% (HR\u00a0=\u00a01.012, 95%CI: 1.007-1.016), and HER2 status (HR\u00a0=\u00a01.195, 95%CI: 1.098-1.301) were independently associated with disease-free survival. Random Forest and XGBoost demonstrated superior and stable predictive performance, with Random Forest achieving time-dependent AUCs of 0.851 (95%CI: 0.802-0.900, 1-year), 0.763 (95%CI: 0.702-0.824, 3-year), and 0.826 (95%CI: 0.766-0.886, 5-year) in the validation set. The Brier scores for Random Forest were consistently low, and calibration metrics confirmed excellent calibration. DCA indicated a positive net benefit across a wide range of threshold probabilities.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This single-center study identifies key prognostic factors for breast cancer and demonstrates that ensemble machine learning models, particularly Random Forest, offer superior predictive power. The integration of SHAP interpretation provides a methodological framework for potential clinical application. However, all predictive models require external, multi-center validation before clinical consideration. These findings provide a promising methodological basis, but caution is warranted against overinterpretation until independent verification is complete.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2026.1830769","type":"journal-article","created":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T05:37:58Z","timestamp":1785217078000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploring prognostic factors in breast cancer: development and selection of optimal machine learning models"],"prefix":"10.3389","volume":"16","author":[{"given":"Meiying","family":"Shen","sequence":"first","affiliation":[{"name":"Department of Breast Surgery, Maoming People\u2019s Hospital","place":["Maoming, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yulei","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Breast Surgery, Guangdong Provincial People\u2019s Hospital","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zongyuan","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Breast Surgery, Maoming People\u2019s Hospital","place":["Maoming, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lifei","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Ultrasound, Maoming People\u2019s Hospital","place":["Maoming, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaofeng","family":"Wu","sequence":"additional","affiliation":[{"name":"Department of Ultrasound, Maoming People\u2019s Hospital","place":["Maoming, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huawen","family":"Pan","sequence":"additional","affiliation":[{"name":"Department of Spine Surgery, Maoming People\u2019s Hospital","place":["Maoming, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Breast and Thyroid Surgery, Guangzhou First People\u2019s Hospital","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,28]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21660","article-title":"Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"71","author":"Sung","year":"2021","journal-title":"CA Cancer J Clin"},{"key":"B2","doi-asserted-by":"publisher","first-page":"394","DOI":"10.3322\/caac.21492","article-title":"Global cancer statistics 2018: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"68","author":"Bray","year":"2018","journal-title":"CA Cancer J Clin"},{"key":"B3","doi-asserted-by":"publisher","first-page":"288","DOI":"10.1001\/jama.2018.19323","article-title":"Breast cancer treatment: a review","volume":"321","author":"Waks","year":"2019","journal-title":"JAMA"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1038\/nrclinonc.2011.214","article-title":"Breast cancer","volume":"389","author":"Harbeck","year":"2017","journal-title":"Lancet"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1093\/annonc\/mdt303","article-title":"Personalizing the treatment of women with early breast cancer: highlights of the St Gallen International Expert Consensus on the Primary Therapy of Early Breast Cancer 2013","volume":"24","author":"Goldhirsch","year":"2013","journal-title":"Ann Oncol"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1634\/theoncologist.9-6-606","article-title":"Prognostic and predictive factors in early-stage breast cancer","volume":"9","author":"Cianfrocca","year":"2004","journal-title":"Oncologist"},{"key":"B7","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1186\/bcr2607","article-title":"Breast cancer prognostic classification in the molecular era: the role of histological grade","volume":"12","author":"Rakha","year":"2010","journal-title":"Breast Cancer Res"},{"key":"B8","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1186\/s12885-019-5442-6","article-title":"Prognostic models for breast cancer: a systematic review","volume":"19","author":"Phung","year":"2019","journal-title":"BMC Cancer"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2011.02.013","article-title":"Hallmarks of cancer: the next generation","volume":"144","author":"Hanahan","year":"2011","journal-title":"Cell"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1016\/b978-0-12-801238-3.65801-4","article-title":"Cancer-related inflammation","volume":"454","author":"Mantovani","year":"2008","journal-title":"Nature"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1093\/jnci\/dju124","article-title":"Prognostic role of neutrophil-to-lymphocyte ratio in solid tumors: a systematic review and meta-analysis","volume":"106","author":"Templeton","year":"2014","journal-title":"J Natl Cancer Inst"},{"key":"B12","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1186\/s13058-016-0794-1","article-title":"Prognostic role of neutrophil-to-lymphocyte ratio in breast cancer: a systematic review and meta-analysis","volume":"19","author":"Ethier","year":"2017","journal-title":"Breast Cancer Res"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2010.01.025","article-title":"Immunity, inflammation, and cancer","volume":"140","author":"Grivennikov","year":"2010","journal-title":"Cell"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1056\/nejmp1606181","article-title":"Predicting the future - big data, machine learning, and clinical medicine","volume":"375","author":"Obermeyer","year":"2016","journal-title":"N Engl J Med"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1161\/circulationaha.120.050583","article-title":"Machine learning in medicine","volume":"132","author":"Deo","year":"2015","journal-title":"Circulation"},{"key":"B16","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1186\/s12874-019-0681-4","article-title":"Machine learning in medicine: a practical introduction","volume":"19","author":"Sidey-Gibbons","year":"2019","journal-title":"BMC Med Res Methodol"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1056\/nejmra1814259","article-title":"Machine learning in medicine","volume":"380","author":"Rajkomar","year":"2019","journal-title":"N Engl J Med"},{"key":"B18","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1016\/j.csbj.2014.11.005","article-title":"Machine learning applications in cancer prognosis and prediction","volume":"13","author":"Kourou","year":"2015","journal-title":"Comput Struct Biotechnol J"},{"key":"B19","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1177\/117693510600200030","article-title":"Applications of machine learning in cancer prediction and prognosis","volume":"2","author":"Cruz","year":"2007","journal-title":"Cancer Inform"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1038\/nature21056","article-title":"Dermatologist-level classification of skin cancer with deep neural networks","volume":"542","author":"Esteva","year":"2017","journal-title":"Nature"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1038\/s41568-018-0016-5","article-title":"Artificial intelligence in radiology","volume":"18","author":"Hosny","year":"2018","journal-title":"Nat Rev Cancer"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1705.07874","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2014.11.010","article-title":"Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD statement","volume":"350","author":"Collins","year":"2015","journal-title":"BMJ"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1007\/s12094-015-1391-y","article-title":"Prognostic value of tumor size in breast cancer: a systematic review","volume":"179","author":"Yu","year":"2020","journal-title":"Breast Cancer Res Treat"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1007\/s10549-016-3721-3","article-title":"Estrogen receptor status and prognosis in breast cancer: a meta-analysis","volume":"36","author":"Liu","year":"2018","journal-title":"J Clin Oncol"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1023\/a:1014778713034","article-title":"Prognostic factors in breast cancer: current and new predictors of metastasis","volume":"6","author":"Hayes","year":"2001","journal-title":"J Mammary Gland Biol Neoplasia"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1002\/1097-0142(19890101)63:1<181::aid-cncr2820630129>3.0.co;2-h","article-title":"Relation of tumor size, lymph node status, and survival in 24,740 breast cancer cases","volume":"63","author":"Carter","year":"1989","journal-title":"Cancer"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.3747\/co.19.1043","article-title":"Tumour size predicts long-term survival among women with lymph node-positive breast cancer","volume":"19","author":"Narod","year":"2012","journal-title":"Curr Oncol"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(05)66544-0","article-title":"Effects of chemotherapy and hormonal therapy for early breast cancer on recurrence and 15-year survival: an overview of the randomised trials","volume":"365","year":"2005","journal-title":"Lancet"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(11)60993-8","article-title":"Relevance of breast cancer hormone receptors and other factors to the efficacy of adjuvant tamoxifen: patient-level meta-analysis of randomised trials","volume":"378","author":"Davies","year":"2011","journal-title":"Lancet"},{"key":"B31","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1056\/nejmoa2203690","article-title":"Trastuzumab deruxtecan in previously treated HER2-low advanced breast cancer","volume":"387","author":"Modi","year":"2022","journal-title":"N Engl J Med"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1007\/s10549-015-3559-0","article-title":"Prognostic value of Ki-67 in breast cancer: a systematic review and meta-analysis","volume":"152","author":"Petrelli","year":"2015","journal-title":"Breast Cancer Res Treat"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1056\/nejmoa1607303","article-title":"Palbociclib and letrozole in advanced breast cancer","volume":"375","author":"Finn","year":"2016","journal-title":"N Engl J Med"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1056\/nejmoa1609709","article-title":"Ribociclib as first-line therapy for HR-positive, advanced breast cancer","volume":"375","author":"Hortobagyi","year":"2016","journal-title":"N Engl J Med"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejca.2011.03.028","article-title":"A comparison of inflammation-based prognostic scores in patients with cancer. A Glasgow Inflammation Outcome Study","volume":"47","author":"Proctor","year":"2011","journal-title":"Eur J Cancer"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2017.11470","article-title":"Effect of axillary dissection vs no axillary dissection on 10-year overall survival among women with invasive breast cancer and sentinel node metastasis: the ACOSOG Z0011 (Alliance) randomized clinical trial","volume":"318","author":"Giuliano","year":"2017","journal-title":"JAMA"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0007695","article-title":"Breast cancer in young women: poor survival despite intensive treatment","volume":"4","author":"Fredholm","year":"2009","journal-title":"PloS One"},{"key":"B38","doi-asserted-by":"publisher","DOI":"10.1002\/sim.6787","article-title":"Sample size considerations for the external validation of a multivariable prognostic model: a resampling study","volume":"35","author":"Collins","year":"2016","journal-title":"Stat Med"},{"key":"B39","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1038\/s41576-018-0071-5","article-title":"Current and future perspectives of liquid biopsies in genomics-driven oncology","volume":"20","author":"Heitzer","year":"2019","journal-title":"Nat Rev Genet"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1830769\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T05:38:00Z","timestamp":1785217080000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1830769\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,28]]},"references-count":39,"alternative-id":["10.3389\/fonc.2026.1830769"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2026.1830769","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,28]]},"article-number":"1830769"}}