{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T08:46:41Z","timestamp":1782895601550,"version":"3.54.5"},"reference-count":36,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"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>Background<\/jats:title>\n                    <jats:p>Patients with synchronous metastatic nasopharyngeal carcinoma (smNPC) show marked survival heterogeneity, which complicates individualized prognostic assessment and treatment planning. We developed and validated a stacking ensemble machine learning model for predicting 3-year overall survival (OS) in this population.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This multicenter retrospective study included 413 patients from three institutions, randomly assigned to a training set (n = 289) and an internal held-out validation set (n = 124). Candidate predictors included demographic, histopathologic, serological, and treatment-related variables. The 3-year OS label was assigned only when death occurred within 3 years or when follow-up confirmed survival at 3 years. Six base learners were trained: gradient boosting decision tree (GBDT), adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), categorical boosting (CatBoost), and random forest (RF). Hard voting, soft voting, and stacking ensembles were constructed and compared. Discrimination, calibration, decision curve analysis, leave-one-center-out (LOCO) validation, overfitting diagnostics, and Shapley Additive Explanations (SHAP) were assessed.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The stacking ensemble achieved the highest internal held-out validation AUC of 0.8358 for 3-year OS prediction. The 3-year death event rate was 60.0% overall, 59.9% in the training set, and 60.5% in the internal held-out validation set. After multiplicity adjustment, stacking showed significantly higher AUC than GBDT, AdaBoost, and hard voting, whereas differences versus other comparators were not significant. Overfitting diagnostics showed a training AUC of 0.9150, an optimism gap of 0.0792, and an optimism-corrected AUC of 0.8415. SHAP identified immunotherapy, first-line regimen, number of metastatic lesions, and number of metastatic organs as influential predictors.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The stacking ensemble model provided an interpretable approach for individualized 3-year OS prediction in smNPC and may support multidisciplinary prognostic assessment, although prospective validation remains needed.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2026.1866690","type":"journal-article","created":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T08:05:22Z","timestamp":1782893122000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Predicting overall survival in synchronous metastatic nasopharyngeal carcinoma using a stacking ensemble machine learning model: a multicenter retrospective study"],"prefix":"10.3389","volume":"16","author":[{"given":"Canwen","family":"Che","sequence":"first","affiliation":[{"name":"Shantou University Medical College","place":["Shantou, China"]},{"name":"Department of Radiation Oncology, The People\u2019s Hospital of Baoan Shenzhen","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanyue","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Radiology, Xiangtan Central Hospital","place":["Xiangtan, Hunan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Ma","sequence":"additional","affiliation":[{"name":"Medical Imaging Department, Guangxi Medical University Cancer Hospital","place":["Nanning, Guangxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haibo","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Radiology, Xiangtan Central Hospital","place":["Xiangtan, Hunan, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wentao","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, The People\u2019s Hospital of Baoan Shenzhen","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhanhong","family":"Tan","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, The People\u2019s Hospital of Baoan Shenzhen","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, The People\u2019s Hospital of Baoan Shenzhen","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyi","family":"Zeng","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, Wuzhou Red Cross Hospital","place":["Wuzhou, Guangxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiwen","family":"Duan","sequence":"additional","affiliation":[{"name":"Department of Radiation Oncology, The People\u2019s Hospital of Baoan Shenzhen","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanxun","family":"Cheng","sequence":"additional","affiliation":[{"name":"Department of Radiology, Peking University Shenzhen Hospital","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,1]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1016\/j.oraloncology.2024.106834","article-title":"Establishing subdivisions of M1 stage nasopharyngeal carcinoma based on decision tree classification: a multicenter retrospective study","volume":"153","author":"Liu","year":"2024","journal-title":"Oral Oncol"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1002\/hed.27895","article-title":"Machine learning-derived prognostic signature for progression-free survival in non-metastatic nasopharyngeal carcinoma","volume":"47","author":"Zuo","year":"2025","journal-title":"Head Neck"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejca.2017.02.029","article-title":"Establishment and validation of M1 stage subdivisions for de novo metastatic nasopharyngeal carcinoma to better predict prognosis and guide treatment","volume":"77","author":"Zou","year":"2017","journal-title":"Eur J Cancer"},{"key":"B4","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1016\/j.critrevonc.2017.03.030","article-title":"Palliative systemic therapy for recurrent or metastatic nasopharyngeal carcinoma: how far have we achieved","volume":"114","author":"Lee","year":"2017","journal-title":"Crit Rev Oncol Hematol"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1001\/jamaoncol.2020.1808","article-title":"Efficacy and safety of locoregional radiotherapy with chemotherapy vs chemotherapy alone in de novo metastatic nasopharyngeal carcinoma: a multicenter phase 3 randomized clinical trial","volume":"6","author":"You","year":"2020","journal-title":"JAMA Oncol"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1016\/j.oraloncology.2022.105736","article-title":"Refining TNM 8 M1 categories with anatomic subgroups for previously untreated de novo metastatic nasopharyngeal carcinoma","volume":"126","author":"Chan","year":"2022","journal-title":"Oral Oncol"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1007\/s12094-023-03344-w","article-title":"Predictive progression outcomes and risk stratification in patients with recurrent or metastatic nasopharyngeal carcinoma who received first-line immunochemotherapy","volume":"26","author":"He","year":"2024","journal-title":"Clin Transl Oncol"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2024.110311","article-title":"Efficacy of metastatic lesion radiotherapy in patients with metastatic nasopharyngeal carcinoma: a multicenter retrospective study","volume":"196","author":"Liu","year":"2024","journal-title":"Radiother Oncol"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1002\/cam4.6764","article-title":"Long-term outcomes of metastasis-directed stereotactic body radiation therapy in metastatic nasopharyngeal carcinoma","volume":"13","author":"Yang","year":"2024","journal-title":"Cancer Med"},{"key":"B10","doi-asserted-by":"publisher","first-page":"3950","DOI":"10.1038\/s41598-024-54230-6","article-title":"Risk-adapted locoregional radiotherapy strategies based on a prognostic nomogram for de novo metastatic nasopharyngeal carcinoma patients treated with chemoimmunotherapy","volume":"14","author":"Chen","year":"2024","journal-title":"Sci Rep"},{"key":"B11","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1186\/s13014-025-02602-1","article-title":"Prognostic nomogram for synchronous metastatic nasopharyngeal carcinoma: a retrospective multicentre study","volume":"20","author":"Zeng","year":"2025","journal-title":"Radiat Oncol"},{"key":"B12","first-page":"281","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"Bergstra","year":"2012","journal-title":"J Mach Learn Res"},{"key":"B13","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1109\/MCI.2015.2471235","article-title":"Ensemble classification and regression: recent developments, applications and future directions","volume":"11","author":"Ren","year":"2016","journal-title":"IEEE Comput Intell Mag"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1186\/s13244-025-02097-0","article-title":"Intratumoral heterogeneity score enhances invasiveness prediction in pulmonary ground-glass nodules via stacking ensemble machine learning","volume":"16","author":"Zuo","year":"2025","journal-title":"Insights Imaging"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Collins","year":"2024","journal-title":"BMJ"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.b2393","article-title":"Multiple imputation for missing data in epidemiological and clinical research: potential and pitfalls","volume":"338","author":"Sterne","year":"2009","journal-title":"BMJ"},{"key":"B17","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-16399-0","volume-title":"Clinical Prediction Models: A Practical Approach to Development, Validation, and Updating","author":"Steyerberg","year":"2019"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1002\/cncr.25932","article-title":"Plasma Epstein-Barr virus DNA level strongly predicts survival in metastatic\/recurrent nasopharyngeal carcinoma treated with palliative chemotherapy","volume":"117","author":"An","year":"2011","journal-title":"Cancer"},{"key":"B19","doi-asserted-by":"publisher","first-page":"796","DOI":"10.1177\/0962280214558972","article-title":"Events per variable and the relative performance of different strategies for estimating the out-of-sample validity of logistic regression models","volume":"26","author":"Austin","year":"2017","journal-title":"Stat Methods Med Res"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.2307\/2531595","article-title":"Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach","volume":"44","author":"DeLong","year":"1988","journal-title":"Biometrics"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1997.10474007","article-title":"Improvements on cross-validation: the .632+ bootstrap method","volume":"92","author":"Efron","year":"1997","journal-title":"J Am Stat Assoc"},{"key":"B22","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1186\/s12885-025-14259-w","article-title":"Stacking classifiers based on an integrated machine learning model: fusion of computed tomography radiomics and clinical biomarkers to predict lymph node metastasis in locally advanced gastric cancer after neoadjuvant chemotherapy","volume":"25","author":"Ling","year":"2025","journal-title":"BMC Cancer"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1177\/15330338251351365","article-title":"Ensemble machine learning classifiers combining computed tomography radiomics and clinical radiological features for preoperative prediction of pathological invasiveness in lung adenocarcinoma presenting as part-solid nodules: a multicenter retrospective study","volume":"24","author":"Li","year":"2025","journal-title":"Technol Cancer Res Treat"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(16)31388-5","article-title":"Gemcitabine plus cisplatin versus fluorouracil plus cisplatin in recurrent or metastatic nasopharyngeal carcinoma: a multicentre, randomised, open-label, phase 3 trial","volume":"388","author":"Zhang","year":"2016","journal-title":"Lancet"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.4103\/sjmms.sjmms_471_20","article-title":"Gemcitabine plus platinum versus docetaxel plus platinum as first-line therapy for metastatic nasopharyngeal carcinoma: a randomized clinical study","volume":"9","author":"Yang","year":"2021","journal-title":"Saudi J Med Med Sci"},{"key":"B26","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1200\/JCO.1995.13.1.8","article-title":"Oligometastases","volume":"13","author":"Hellman","year":"1995","journal-title":"J Clin Oncol"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1001\/jamaoncol.2024.4354","article-title":"Ninth version of the AJCC and UICC nasopharyngeal cancer TNM staging classification","volume":"10","author":"Pan","year":"2024","journal-title":"JAMA Oncol"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1016\/j.ccell.2023.12.020","article-title":"Refining the 8th edition TNM classification for EBV-related nasopharyngeal carcinoma","volume":"42","author":"Du","year":"2024","journal-title":"Cancer Cell"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1016\/j.tranon.2021.101187","article-title":"Effects of locoregional radiotherapy in de novo metastatic nasopharyngeal carcinoma: a real-world study","volume":"14","author":"Zeng","year":"2021","journal-title":"Transl Oncol"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1002\/hed.26753","article-title":"Identifying the optimal candidates for locoregional radiation therapy in patients with de novo metastatic nasopharyngeal carcinoma","volume":"43","author":"Xu","year":"2021","journal-title":"Head Neck"},{"key":"B31","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1016\/S1470-2045(21)00302-8","article-title":"Camrelizumab versus placebo in combination with gemcitabine and cisplatin as first-line treatment for recurrent or metastatic nasopharyngeal carcinoma (CAPTAIN-1st): a multicentre, randomised, double-blind, phase 3 trial","volume":"22","author":"Yang","year":"2021","journal-title":"Lancet Oncol"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2023.20181","article-title":"Toripalimab plus chemotherapy for recurrent or metastatic nasopharyngeal carcinoma: the JUPITER-02 randomized clinical trial","volume":"330","author":"Mai","year":"2023","journal-title":"JAMA"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1177\/15353508241261473","article-title":"Comparison of tumor non-specific and PD-L1-specific imaging by near-infrared fluorescence\/Cerenkov luminescence dual-modality in-situ imaging","volume":"23","author":"Zhang","year":"2024","journal-title":"Mol Imaging"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2019.00433","article-title":"Differentiation between G1 and G2\/G3 phyllodes tumors of breast using mammography and mammographic texture analysis","volume":"9","author":"Cui","year":"2019","journal-title":"Front Oncol"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1007\/s00261-021-02954-8","article-title":"Preoperative differentiation of serous cystic neoplasms from mucin-producing pancreatic cystic neoplasms using a computed tomography-based radiomics nomogram","volume":"46","author":"Chen","year":"2021","journal-title":"Abdom Radiol (NY)"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1866690\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T08:05:24Z","timestamp":1782893124000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1866690\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,1]]},"references-count":36,"alternative-id":["10.3389\/fonc.2026.1866690"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2026.1866690","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,1]]},"article-number":"1866690"}}