{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T06:09:12Z","timestamp":1775628552205,"version":"3.50.1"},"reference-count":42,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T00:00:00Z","timestamp":1775606400000},"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. Med."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Breast cancer is the most common malignancy worldwide. Brain metastasis in breast cancer severely impacts prognosis, and the objective of this study is to develop a machine learning model for predicting the risk of brain metastasis in breast cancer patients to assist clinical management.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Univariate and multivariate logistic regression analyses were employed to screen the final included variables, and eight machine learning algorithms were utilized for model construction. Model performance was evaluated using receiver operating characteristic curves, precision-recall curves, decision curve analysis (DCA), and calibration curves, with the optimal model selected based on these metrics. The model was trained on a cohort of 154,193 patients, internally validated on 66,084 patients, and externally validated on 765 real-world cases, incorporating metrics such as area under the curve (AUC), area under the precision-recall curve (AUPRC), decision curves, and calibration plots, while SHAP analysis was applied to enhance interpretability. A web-based calculator was developed based on the optimal model to facilitate clinical application.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Univariate logistic regression identified higher tumor grade, advanced T\/N stage, advanced clinical stage, and PR positivity as risk factors, whereas radiotherapy, chemotherapy, surgery, HR + \/HER2- subtype, and unilateral tumors served as protective factors (\n                      <jats:italic>P<\/jats:italic>\n                      &amp;lt; 0.001). Multivariate analysis confirmed independent risk factors, including poorer pathological grade, N3 lymph node status, later stage, and PR positivity, and protective factors, including radiotherapy, chemotherapy, surgery, non-HR-\/HER2- subtypes, and HER2 positivity. The XGBoost model achieved an AUC of 0.98 in 10-fold cross-validation, with AUCs of 0.99 and 0.97 in the internal test set and external validation set, respectively; AUPRC values were 0.933, 0.864, and 0.648; decision curve analysis demonstrated superior net benefit compared to alternative models within the 0.1\u20130.8 threshold range; calibration curves showed high concordance between predicted and observed event rates. SHAP analysis highlighted surgery as the primary protective factor, followed by stage and T classification as risk enhancers, revealing interactions among treatment variables.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This study developed an interpretable and clinically deployable XGB model, accompanied by a web-based calculator, thereby advancing personalized risk stratification, early screening, and resource optimization in the management of breast cancer brain metastasis.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1693557","type":"journal-article","created":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T05:32:16Z","timestamp":1775626336000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["An interpretable machine learning model for predicting brain metastasis in breast cancer"],"prefix":"10.3389","volume":"13","author":[{"given":"Hong","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Breast Surgery, First Ward, Tangshan People\u2019s Hospital, Tangshan","place":["Hebei, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Breast Surgery, First Ward, Tangshan People\u2019s Hospital, Tangshan","place":["Hebei, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Chang","sequence":"additional","affiliation":[{"name":"Department of Breast Surgery, First Ward, Tangshan People\u2019s Hospital, Tangshan","place":["Hebei, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingjing","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Breast Surgery, First Ward, Tangshan People\u2019s Hospital, Tangshan","place":["Hebei, China"]},{"name":"Hebei Key Laboratory of Molecular Oncology, Tangshan","place":["Hebei, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Binxu","family":"Qiu","sequence":"additional","affiliation":[{"name":"Breast Center, West China Hospital, Sichuan University","place":["Chengdu, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Breast Center, The Fourth Hospital of Hebei Medical University","place":["Shijiazhuang, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Gao","sequence":"additional","affiliation":[{"name":"Department of Radiotherapy, The Fourth Hospital of Hebei Medical University","place":["Shijiazhuang, China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,4,8]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1134","DOI":"10.1016\/S0140-6736(16)31891-8","article-title":"Breast cancer.","volume":"389","author":"Harbeck","year":"2017","journal-title":"Lancet."},{"key":"B2","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1097\/PPO.0000000000000503","article-title":"Triple-negative breast cancer central nervous system metastases from the laboratory to the clinic.","volume":"27","author":"Zimmer","year":"2021","journal-title":"Cancer J."},{"key":"B3","doi-asserted-by":"publisher","first-page":"894","DOI":"10.1093\/neuonc\/noaa285","article-title":"The incidence of brain metastases among patients with metastatic breast cancer: a systematic review and meta-analysis.","volume":"23","author":"Kuksis","year":"2021","journal-title":"Neuro Oncol."},{"key":"B4","doi-asserted-by":"publisher","first-page":"5","DOI":"10.5306\/wjco.v15.i1.5","article-title":"Prognostic factors of breast cancer brain metastasis.","volume":"15","author":"Yakar","year":"2024","journal-title":"World J Clin Oncol."},{"key":"B5","doi-asserted-by":"publisher","first-page":"2638","DOI":"10.1002\/cncr.23930","article-title":"Sites of distant recurrence and clinical outcomes in patients with metastatic triple-negative breast cancer: high incidence of central nervous system metastases.","volume":"113","author":"Lin","year":"2008","journal-title":"Cancer."},{"key":"B6","doi-asserted-by":"publisher","first-page":"102448","DOI":"10.1016\/j.canep.2023.102448","article-title":"A brain metastasis prediction model in women with breast cancer.","volume":"86","author":"Cacho-D\u00edaz","year":"2023","journal-title":"Cancer Epidemiol."},{"key":"B7","doi-asserted-by":"publisher","first-page":"1969","DOI":"10.3390\/cancers15071969","article-title":"Empirical study of overfitting in deep learning for predicting breast cancer metastasis.","volume":"15","author":"Xu","year":"2023","journal-title":"Cancers."},{"key":"B8","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1186\/s12967-023-04277-2","article-title":"Novel models by machine learning to predict prognosis of breast cancer brain metastases.","volume":"21","author":"Li","year":"2023","journal-title":"J Transl Med."},{"key":"B9","doi-asserted-by":"publisher","first-page":"1348","DOI":"10.1200\/OP.23.00794","article-title":"Breast cancer brain metastasis: a comprehensive review.","volume":"10","author":"Raghavendra","year":"2024","journal-title":"JCO Oncol Pract."},{"key":"B10","doi-asserted-by":"publisher","first-page":"e823","DOI":"10.1016\/j.wneu.2019.04.262","article-title":"Nomogram-predicted survival of breast cancer brain metastasis: a SEER-based population study.","volume":"128","author":"Xiong","year":"2019","journal-title":"World Neurosurg."},{"key":"B11","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1080\/13696998.2024.2439228","article-title":"Real-world perioperative treatment patterns and economic burden of recurrence in early-stage HER2-negative breast cancer: a SEER-Medicare study.","volume":"28","author":"Earla","year":"2025","journal-title":"J Med Econ."},{"key":"B12","doi-asserted-by":"publisher","first-page":"e94","DOI":"10.1097\/PAS.0000000000000749","article-title":"The surveillance, epidemiology, and end results (SEER) program and pathology: toward strengthening the critical relationship.","volume":"40","author":"Duggan","year":"2016","journal-title":"Am J Surg Pathol."},{"key":"B13","doi-asserted-by":"publisher","first-page":"2536627","DOI":"10.1080\/08941939.2025.2536627","article-title":"A novel nomogram for prediction of survival in patients with small isolated hepatocellular carcinoma: a population-based and externally validated study.","volume":"38","author":"Li","year":"2025","journal-title":"J Invest Surg."},{"key":"B14","doi-asserted-by":"publisher","first-page":"2259","DOI":"10.1016\/j.asjsur.2021.12.037","article-title":"Brain metastasis in de novo breast cancer: an updated population-level study from SEER database.","volume":"45","author":"Sun","year":"2022","journal-title":"Asian J Surg."},{"key":"B15","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1016\/j.jor.2025.12.024","article-title":"mModPoEs: multimodal posture estimation and feedback-driven correction of load-bearing human movements using wearable sensors and computer vision.","volume":"73","author":"Gokul Thilaak","year":"2025","journal-title":"J Orthop."},{"key":"B16","doi-asserted-by":"publisher","first-page":"134023","DOI":"10.1016\/j.ijcard.2025.134023","article-title":"Sex differences in plaque burden and outcomes in symptomatic patients with suspected coronary artery disease.","volume":"444","author":"Molnar","year":"2026","journal-title":"Int J Cardiol."},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1080\/02770903.2026.2618108","article-title":"Prediction model for cardiovascular mortality risk in asthma patients based on machine learning.","author":"Wang","year":"2026","journal-title":"J Asthma."},{"key":"B18","doi-asserted-by":"publisher","first-page":"106239","DOI":"10.1016\/j.ijmedinf.2025.106239","article-title":"Graph attention network with comorbidity connectivity embedding for post-traumatic epilepsy risk prediction using sparse time-series electronic health records.","volume":"208","author":"Ramamurthy","year":"2026","journal-title":"Int J Med Inform."},{"key":"B19","doi-asserted-by":"publisher","first-page":"2606571","DOI":"10.1080\/07853890.2025.2606571","article-title":"Development and validation of an interpretable Random Forest model for predicting recurrence after endoscopic submucosal dissection in superficial oesophageal squamous cell carcinoma.","volume":"58","author":"Zhu","year":"2026","journal-title":"Ann Med."},{"key":"B20","doi-asserted-by":"publisher","first-page":"e0338928","DOI":"10.1371\/journal.pone.0338928","article-title":"Mung bean seed classification based on multimodal features and Kepler-optimized stacking ensemble learning model.","volume":"21","author":"Song","year":"2026","journal-title":"PLoS One."},{"key":"B21","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1186\/s12911-025-03116-2","article-title":"Optimized feature selection and advanced machine learning for stroke risk prediction in revascularized coronary artery disease patients.","volume":"25","author":"Si","year":"2025","journal-title":"BMC Med Inform Decis Mak."},{"key":"B22","doi-asserted-by":"publisher","first-page":"1065468","DOI":"10.3389\/fonc.2022.1065468","article-title":"Application of machine learning techniques in real-world research to predict the risk of liver metastasis in rectal cancer.","volume":"12","author":"Qiu","year":"2022","journal-title":"Front Oncol."},{"key":"B23","doi-asserted-by":"publisher","first-page":"249","DOI":"10.3390\/jpm13020249","article-title":"Nomograms for predicting disease-free survival based on core needle biopsy and surgical specimens in female breast cancer patients with non-pathological complete response to neoadjuvant chemotherapy.","volume":"13","author":"Lan","year":"2023","journal-title":"J Pers Med."},{"key":"B24","doi-asserted-by":"publisher","first-page":"1112","DOI":"10.3390\/medicina61061112","article-title":"Interpretable machine learning for serum-based metabolomics in breast cancer diagnostics: insights from multi-objective feature selection-driven LightGBM-SHAP models.","volume":"61","author":"Guldogan","year":"2025","journal-title":"Medicina."},{"key":"B25","doi-asserted-by":"publisher","first-page":"472","DOI":"10.1007\/s12672-025-02211-0","article-title":"Developing a prognostic nomogram for primary thyroid lymphoma: insights from a large retrospective study.","volume":"16","author":"Gao","year":"2025","journal-title":"Discov Oncol."},{"key":"B26","doi-asserted-by":"publisher","first-page":"2974","DOI":"10.1111\/liv.15042","article-title":"Development of pre and post-operative nomograms to predict individual survival for ideal liver resection candidates with hepatocellular carcinoma.","volume":"41","author":"Zeng","year":"2021","journal-title":"Liver Int."},{"key":"B27","doi-asserted-by":"publisher","first-page":"2541316","DOI":"10.1080\/07853890.2025.2541316","article-title":"Machine learning and SHAP value interpretation for predicting the response to neoadjuvant chemotherapy and long-term clinical outcomes in Chinese female breast cancer.","volume":"57","author":"Yuan","year":"2025","journal-title":"Ann Med."},{"key":"B28","doi-asserted-by":"publisher","first-page":"e0329308","DOI":"10.1371\/journal.pone.0329308","article-title":"Prevalence and clinicopathological characteristics of breast cancer patients with brain metastases in Ghana: a single-center cross-sectional study.","volume":"20","author":"Daniels","year":"2025","journal-title":"PLoS One."},{"key":"B29","doi-asserted-by":"publisher","first-page":"973","DOI":"10.1186\/s12885-025-13677-0","article-title":"Re-resection of brain metastases - outcomes of an institutional cohort study and literature review.","volume":"25","author":"Wasilewski","year":"2025","journal-title":"BMC Cancer."},{"key":"B30","doi-asserted-by":"publisher","first-page":"606","DOI":"10.1007\/s00066-025-02378-z","article-title":"Radiotherapy in breast cancer brain metastases: the impact of time interval and disease dynamics when breast cancer seeds to the brain.","volume":"201","author":"Hintelmann","year":"2025","journal-title":"Strahlenther Onkol."},{"key":"B31","doi-asserted-by":"publisher","first-page":"12034","DOI":"10.3390\/ijms241512034","article-title":"Navigating the blood-brain barrier: challenges and therapeutic strategies in breast cancer brain metastases.","volume":"24","author":"Terceiro","year":"2023","journal-title":"Int J Mol Sci."},{"key":"B32","doi-asserted-by":"publisher","first-page":"26717","DOI":"10.1038\/s41598-025-12883-x","article-title":"Patterns and prognostic implications of distant metastasis in breast cancer based on SEER population data.","volume":"15","author":"Zhang","year":"2025","journal-title":"Sci Rep."},{"key":"B33","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1007\/s11060-014-1704-y","article-title":"Predicting early brain metastases based on clinicopathological factors and gene expression analysis in advanced HER2-positive breast cancer patients.","volume":"122","author":"Duchnowska","year":"2015","journal-title":"J Neurooncol."},{"key":"B34","doi-asserted-by":"publisher","first-page":"3976","DOI":"10.3390\/ijms25073976","article-title":"B7-H3 expression in breast cancer and brain metastasis.","volume":"25","author":"Joshi","year":"2024","journal-title":"Int J Mol Sci."},{"key":"B35","doi-asserted-by":"publisher","first-page":"vdab009","DOI":"10.1093\/noajnl\/vdab009","article-title":"Factors affecting time to brain metastases for stage 2 and 3 breast cancer patients: a large single-institutional analysis with potential screening implications.","volume":"3","author":"Cao","year":"2021","journal-title":"Neurooncol Adv."},{"key":"B36","doi-asserted-by":"publisher","first-page":"1010428317705082","DOI":"10.1177\/1010428317705082","article-title":"The effect of distant metastases sites on survival in de novo stage-IV breast cancer: a SEER database analysis.","volume":"39","author":"Wu","year":"2017","journal-title":"Tumour Biol."},{"key":"B37","doi-asserted-by":"publisher","first-page":"1262","DOI":"10.1186\/s12885-024-12983-3","article-title":"Development of graded prognostic assessment for breast Cancer brain metastasis incorporating extracranial metastatic features: a retrospective analysis of 284 patients.","volume":"24","author":"Wang","year":"2024","journal-title":"BMC Cancer."},{"key":"B38","doi-asserted-by":"publisher","first-page":"104269","DOI":"10.1016\/j.critrevonc.2024.104269","article-title":"Why does HER2-positive breast cancer metastasize to the brain and what can we do about it?","volume":"195","author":"Xu","year":"2024","journal-title":"Crit Rev Oncol Hematol."},{"key":"B39","doi-asserted-by":"publisher","first-page":"e89389","DOI":"10.1371\/journal.pone.0089389","article-title":"Effect of age and biological subtype on the risk and timing of brain metastasis in breast cancer patients.","volume":"9","author":"Hung","year":"2014","journal-title":"PLoS One."},{"key":"B40","doi-asserted-by":"publisher","first-page":"597","DOI":"10.1056\/NEJMoa1914609","article-title":"Tucatinib, trastuzumab, and capecitabine for HER2-positive metastatic breast cancer.","volume":"382","author":"Murthy","year":"2020","journal-title":"N Engl J Med."},{"key":"B41","doi-asserted-by":"publisher","first-page":"1447508","DOI":"10.3389\/fonc.2024.1447508","article-title":"The multidisciplinary management of HER2-positive breast cancer brain metastases: from new biological insights to future therapeutic options.","volume":"14","author":"von Arx","year":"2024","journal-title":"Front Oncol."},{"key":"B42","doi-asserted-by":"publisher","first-page":"103456","DOI":"10.1016\/j.mex.2025.103456","article-title":"Meteorological drought severity forecasting utilizing blended modelling.","volume":"15","author":"Ahire","year":"2025","journal-title":"MethodsX."}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1693557\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T05:32:18Z","timestamp":1775626338000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1693557\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,8]]},"references-count":42,"alternative-id":["10.3389\/fmed.2026.1693557"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1693557","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,8]]},"article-number":"1693557"}}