{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T05:05:45Z","timestamp":1784264745576,"version":"3.55.0"},"reference-count":21,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T00:00:00Z","timestamp":1784246400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"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>\n                      To investigate the prognostic value of postoperative radiotherapy (RT) for overall survival (OS) in patients with\n                      <jats:italic>de novo<\/jats:italic>\n                      metastatic hormone receptor (HR)-positive breast cancer, and to develop and externally validate a machine learning-based prognostic prediction model to support prognostic risk stratification in patients with or without postoperative radiotherapy.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      2,266 patients with\n                      <jats:italic>de novo<\/jats:italic>\n                      metastatic HR-positive breast cancer from the Surveillance, Epidemiology, and End Results (SEER) database (2010\u20132015) were retrospectively enrolled as the training cohort, and 79 patients from Guangxi Medical University Cancer Hospital (2015\u20132020) served as the independent external validation cohort. OS was compared between the RT and non-RT groups using Kaplan\u2013Meier analysis and the log-rank test. Multivariate Cox regression was performed to identify independent prognostic factors. Four machine learning models\u2014K-nearest neighbors (KNN), logistic regression (LR), random forest (RF), and extreme gradient boosting (XGBoost)\u2014were constructed to predict 3\u2212year OS and evaluated using the area under the receiver operating characteristic curve (AUC), average precision (AP), calibration curves, and decision curve analysis (DCA). Postoperative RT status was included as one of the input features in all models. The predicted outcome reflects 3-year prognostic risk (i.e., probability of death within 3 years) rather than the causal RT benefit.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>In the training cohort, the RT group demonstrated significantly superior OS compared with the non-RT group (HR\u00a0=\u00a00.52, P &amp;lt; 0.001). Multivariate analysis confirmed RT as an independent protective factor for OS (HR\u00a0=\u00a00.657, P &amp;lt; 0.001), a finding further validated in the external validation cohort (HR\u00a0=\u00a00.171, P\u00a0=\u00a00.015). Among the four models, the LR model achieved the best performance, with an AUC of 0.721, an AP of 0.429, and a calibration slope of 0.97. DCA demonstrated favorable net clinical benefit for the LR model.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>\n                      Postoperative RT is an independent protective factor for OS in patients with\n                      <jats:italic>de novo<\/jats:italic>\n                      metastatic HR-positive breast cancer. The LR-based prognostic model provides reliable prognostic risk estimates and may serve as a supportive reference for clinical discussions. This model predicts observed survival risk, not the causal benefit of RT, and should not be used as a standalone tool for treatment decisions.\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2026.1875284","type":"journal-article","created":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T04:22:46Z","timestamp":1784262166000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A machine learning-based prognostic model for de novo metastatic HR-positive breast cancer: SEER cohort with external validation"],"prefix":"10.3389","volume":"16","author":[{"given":"Sihang","family":"Lin","sequence":"first","affiliation":[{"name":"Department of Breast Surgery, Key Laboratory of Breast Cancer Diagnosis and Treatment Research of Guangxi Department of Education, Guangxi Medical University Cancer Hospital","place":["Nanning, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanwan","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Breast Surgery, Key Laboratory of Breast Cancer Diagnosis and Treatment Research of Guangxi Department of Education, Guangxi Medical University Cancer Hospital","place":["Nanning, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lixia","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Breast Surgery, Key Laboratory of Breast Cancer Diagnosis and Treatment Research of Guangxi Department of Education, Guangxi Medical University Cancer Hospital","place":["Nanning, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiayu","family":"Guan","sequence":"additional","affiliation":[{"name":"The Second Clinical Medical College of Jinan University","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chuanrong","family":"Cen","sequence":"additional","affiliation":[{"name":"Department of Breast Surgery, Key Laboratory of Breast Cancer Diagnosis and Treatment Research of Guangxi Department of Education, Guangxi Medical University Cancer Hospital","place":["Nanning, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huawei","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Breast Surgery, Key Laboratory of Breast Cancer Diagnosis and Treatment Research of Guangxi Department of Education, Guangxi Medical University Cancer Hospital","place":["Nanning, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,17]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"12","DOI":"10.3322\/caac.21820","article-title":"Cancer statistics, 2024","volume":"74","author":"Siegel","year":"2024","journal-title":"CA Cancer J Clin"},{"key":"B2","doi-asserted-by":"publisher","first-page":"dju055","DOI":"10.1093\/jnci\/dju055","article-title":"US incidence of breast cancer subtypes defined by joint hormone receptor and HER2 status","volume":"106","author":"Howlader","year":"2014","journal-title":"J Natl Cancer Inst"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1016\/s1470-2045(15)00135-7","article-title":"Locoregional treatment versus no treatment of the primary tumour in metastatic breast cancer: an open-label randomised controlled trial","volume":"16","author":"Badwe","year":"2015","journal-title":"Lancet Oncol"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1097\/sla.0000000000002771","article-title":"Impact of breast surgery in primary metastasized breast cancer: outcomes of the prospective randomized phase III ABCSG-28 POSYTIVE trial","volume":"269","author":"Fitzal","year":"2019","journal-title":"Ann Surg"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1200\/jco.21.02006","article-title":"Early local therapy for the primary site in de novo stage IV breast cancer: results of a randomized clinical trial (EA2108)","volume":"40","author":"Khan","year":"2022","journal-title":"J Clin Oncol"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1038\/s41416-025-03097-z","article-title":"Primary tumour resection plus systemic therapy versus systemic therapy alone in metastatic breast cancer (JCOG1017, PRIM-BC): a randomised clinical trial","volume":"133","author":"Shien","year":"2025","journal-title":"Br J Cancer"},{"key":"B7","doi-asserted-by":"publisher","first-page":"742","DOI":"10.1016\/j.jamcollsurg.2021.08.686","article-title":"Primary surgery with systemic therapy in patients with de novo stage IV breast cancer: 10-year follow-up; protocol MF07-01 randomized clinical trial","volume":"233","author":"Soran","year":"2021","journal-title":"J Am Coll Surg"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.3389\/fendo.2025.1656191","article-title":"Machine learning algorithms for individualized prediction of prognosis in breast cancer liver metastases and the prognostic impact of primary tumor surgery: a multicenter study","volume":"16","author":"Chen","year":"2025","journal-title":"Front Endocrinol (Lausanne)"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.21037\/gs-2025-168","article-title":"SEER-based machine learning prediction of bone metastasis in breast cancer: model development and validation","volume":"14","author":"Gao","year":"2025","journal-title":"Gland Surg"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.4143\/crt.2025.518","article-title":"The impact of post mastectomy radiotherapy on T1-2N0-1 male breast cancer and establishment of an artificial neural network predicting model: population-based study","author":"Huang","year":"2025","journal-title":"Cancer Res Treat"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2024.1470515","article-title":"Nomogram prediction of overall survival in breast cancer patients post-surgery: integrating SEER database and multi-center evidence from China","volume":"14","author":"Zheng","year":"2024","journal-title":"Front Oncol"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1016\/j.breast.2025.104483","article-title":"Options for postoperative radiation therapy in patients with de novo metastatic breast cancer","volume":"82","author":"Li","year":"2025","journal-title":"Breast"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1245\/s10434-010-0985-4","article-title":"The American Joint Committee on Cancer: the 7th edition of the AJCC cancer staging manual and the future of TNM","volume":"17","author":"Edge","year":"2010","journal-title":"Ann Surg Oncol"},{"key":"B14","doi-asserted-by":"publisher","first-page":"648","DOI":"10.3390\/life12050648","article-title":"The R language: an engine for bioinformatics and data science","volume":"12","author":"Giorgi","year":"2022","journal-title":"Life (Basel)"},{"key":"B15","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4757-3294-8","volume-title":"Modeling Survival Data: Extending the Cox Model","author":"Therneau","year":"2000"},{"key":"B16","volume-title":"Survminer: Drawing Survival Curves Using 'Ggplot2'","author":"Kassambara","year":"2021"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v028.i05","article-title":"Building predictive models in R using the caret package","volume":"28","author":"Kuhn","year":"2008","journal-title":"J Stat Software"},{"key":"B18","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/a:1010933404324","article-title":"Random forests","volume":"45","author":"Breiman","year":"2001","journal-title":"Mach Learn"},{"key":"B19","doi-asserted-by":"crossref","DOI":"10.1145\/2939672.2939785","article-title":"XGBoost: a scalable tree boosting system","author":"Chen","year":"2016"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1109\/tit.1967.1053964","article-title":"Nearest neighbor pattern classification","volume":"13","author":"Cover","year":"1967","journal-title":"IEEE Trans Inf Theory"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2288-14-137","article-title":"Modern modelling techniques are data hungry: a simulation study for predicting dichotomous endpoints","volume":"14","author":"van der Ploeg","year":"2014","journal-title":"BMC Med Res Methodol"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1875284\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T04:22:47Z","timestamp":1784262167000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1875284\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,17]]},"references-count":21,"alternative-id":["10.3389\/fonc.2026.1875284"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2026.1875284","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,17]]},"article-number":"1875284"}}