{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T15:08:08Z","timestamp":1779376088017,"version":"3.53.1"},"reference-count":31,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T00:00:00Z","timestamp":1775692800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"publisher","award":["12171328"],"award-info":[{"award-number":["12171328"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Outstanding Young Scientist Program","award":["JWZQ20240101027"],"award-info":[{"award-number":["JWZQ20240101027"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,4,9]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>This paper considers survival analysis of large-scale data distributed across heterogeneous network nodes. We propose a novel method, the Distributed Spanning-Tree-Based Fused Lasso (DSTFL), for Cox regression in distributed settings. By employing a minimum spanning tree-based fusion framework, the method can reduce computational and communication burdens, facilitating scalability to large datasets. Additionally, we develop an efficient alternating direction method of multipliers algorithm for the optimization with privacy protection. We establish large-sample properties and clustering consistency for the proposed estimator. Simulation studies demonstrate that DSTFL improves computational efficiency, clustering performance, and robustness compared to existing methods. An application to Surveillance, Epidemiology, and End Results gastric cancer data illustrates how DSTFL identifies geographically structured survival heterogeneity and heterogeneous covariate effects across regions.<\/jats:p>","DOI":"10.1093\/biomtc\/ujag091","type":"journal-article","created":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T11:38:52Z","timestamp":1778067532000},"source":"Crossref","is-referenced-by-count":0,"title":["Heterogeneity learning in distributed networks with large-scale survival data"],"prefix":"10.1093","volume":"82","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8656-5739","authenticated-orcid":false,"given":"Tingting","family":"Cai","sequence":"first","affiliation":[{"name":"School of Mathematical Sciences, Capital Normal University , Beijing 100048 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4463-004X","authenticated-orcid":false,"given":"Tao","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Mathematical Sciences, Capital Normal University , Beijing 100048 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6946-671X","authenticated-orcid":false,"given":"Jianguo","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Statistics and Data Science, Southern University of Science and Technology , Shenzhen 518055 ,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengqi","family":"Xie","sequence":"additional","affiliation":[{"name":"Department of Biostatistics and Bioinformatics, Duke University , Durham, NC 27705 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,5,21]]},"reference":[{"key":"2026052110405384700_bib1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/2200000016","article-title":"Distributed optimization and statistical learning via the alternating direction method of multipliers","volume":"3","author":"Boyd","year":"2011","journal-title":"Foundations and Trends in Machine Learning"},{"key":"2026052110405384700_bib2","doi-asserted-by":"crossref","first-page":"2215","DOI":"10.1142\/S0218127407018361","article-title":"Optimal path and minimal spanning trees in random weighted networks","volume":"17","author":"Braunstein","year":"2007","journal-title":"International Journal of Bifurcation and Chaos"},{"key":"2026052110405384700_bib3","doi-asserted-by":"crossref","first-page":"S45","DOI":"10.1097\/MLR.0b013e3181d9919f","article-title":"Distributed health data networks: a practical and preferred approach to multi-institutional evaluations of comparative effectiveness, safety, and quality of care","volume":"48","author":"Brown","year":"2010","journal-title":"Medical Care"},{"key":"2026052110405384700_bib4","first-page":"1","article-title":"Heterogeneity-aware clustered distributed learning for multi-source data analysis","volume":"25","author":"Chen","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"2026052110405384700_bib5","doi-asserted-by":"crossref","first-page":"187","DOI":"10.1111\/j.2517-6161.1972.tb00899.x","article-title":"Regression models and life-tables","volume":"34","author":"Cox","year":"1972","journal-title":"Journal of the Royal Statistical Society, Series B (Statistical Methodology)"},{"key":"2026052110405384700_bib6","first-page":"65","article-title":"Distributed learning to protect privacy in multi-centric clinical studies","volume-title":"2015 15th Conference on Artificial Intelligence in Medicine","author":"Damiani","year":"2015"},{"key":"2026052110405384700_bib7","doi-asserted-by":"crossref","first-page":"5076","DOI":"10.1103\/PhysRevLett.86.5076","article-title":"Minimum spanning trees on random networks","volume":"86","author":"Dobrin","year":"2001","journal-title":"Physical Review Letters"},{"key":"2026052110405384700_bib8","first-page":"30","article-title":"ODAL: A one-shot distributed algorithm to perform logistic regressions on electronic health records data from multiple clinical sites","volume-title":"Proceedings of the Pacific Symposium on Biocomputing","author":"Duan","year":"2019"},{"key":"2026052110405384700_bib9","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1093\/biomet\/asab007","article-title":"Heterogeneity-aware and communication-efficient distributed statistical inference","volume":"109","author":"Duan","year":"2022","journal-title":"Biometrika"},{"key":"2026052110405384700_bib10","doi-asserted-by":"crossref","first-page":"8076","DOI":"10.1109\/TIT.2022.3192506","article-title":"An efficient framework for clustered federated learning","volume":"68","author":"Ghosh","year":"2022","journal-title":"IEEE Transactions on Information Theory"},{"key":"2026052110405384700_bib11","first-page":"73","article-title":"Minimum spanning tree based clustering algorithms","volume-title":"2006 18th IEEE International Conference on Tools with Artificial Intelligence","author":"Grygorash","year":"2006"},{"key":"2026052110405384700_bib12","doi-asserted-by":"crossref","first-page":"1695","DOI":"10.1080\/01621459.2024.2443246","article-title":"Robust inference for federated meta-learning","volume":"120","author":"Guo","year":"2025","journal-title":"Journal of the American Statistical Association"},{"key":"2026052110405384700_bib13","first-page":"501","article-title":"Asymptotic properties of nonparametric estimation based on partly interval-censored data","volume":"9","author":"Huang","year":"1999","journal-title":"Statistica Sinica"},{"key":"2026052110405384700_bib14","doi-asserted-by":"crossref","first-page":"175","DOI":"10.1080\/01621459.2014.892882","article-title":"Homogeneity pursuit","volume":"110","author":"Ke","year":"2015","journal-title":"Journal of the American Statistical Association"},{"key":"2026052110405384700_bib15","doi-asserted-by":"crossref","first-page":"489","DOI":"10.1111\/1467-9868.00398","article-title":"Maximum likelihood estimation for the proportional hazards model with partly interval-censored data","volume":"65","author":"Kim","year":"2003","journal-title":"Journal of the Royal Statistical Society, Series B (Statistical Methodology)"},{"key":"2026052110405384700_bib16","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1090\/S0002-9939-1956-0078686-7","article-title":"On the shortest spanning subtree of a graph and the traveling salesman problem","volume":"7","author":"Kruskal","year":"1956","journal-title":"Proceedings of the American Mathematical Society"},{"key":"2026052110405384700_bib17","doi-asserted-by":"crossref","first-page":"1050","DOI":"10.1080\/01621459.2018.1529595","article-title":"Spatial homogeneity pursuit of regression coefficients for large datasets","volume":"114","author":"Li","year":"2019","journal-title":"Journal of the American Statistical Association"},{"key":"2026052110405384700_bib18","first-page":"1","article-title":"Integrative high dimensional multiple testing with heterogeneity under data sharing constraints","volume":"22","author":"Liu","year":"2021","journal-title":"Journal of Machine Learning Research"},{"key":"2026052110405384700_bib19","doi-asserted-by":"crossref","first-page":"1212","DOI":"10.1093\/jamia\/ocv083","article-title":"WebDISCO: a web service for distributed Cox model learning without patient-level data sharing","volume":"22","author":"Lu","year":"2015","journal-title":"Journal of the American Medical Informatics Association"},{"key":"2026052110405384700_bib20","doi-asserted-by":"crossref","first-page":"410","DOI":"10.1080\/01621459.2016.1148039","article-title":"A concave pairwise fusion approach to subgroup analysis","volume":"112","author":"Ma","year":"2017","journal-title":"Journal of the American Statistical Association"},{"key":"2026052110405384700_bib21","doi-asserted-by":"crossref","first-page":"20180026","DOI":"10.1515\/ijb-2018-0026","article-title":"Exploration of heterogeneous treatment effects via concave fusion","volume":"16","author":"Ma","year":"2020","journal-title":"The International Journal of Biostatistics"},{"key":"2026052110405384700_bib22","doi-asserted-by":"crossref","first-page":"1389","DOI":"10.1002\/j.1538-7305.1957.tb01515.x","article-title":"Shortest connection networks and some generalizations","volume":"36","author":"Prim","year":"1957","journal-title":"The Bell System Technical Journal"},{"key":"2026052110405384700_bib23","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1214\/aos\/1176344136","article-title":"Estimating the dimension of a model","volume":"6","author":"Schwarz","year":"1978","journal-title":"The Annals of Statistics"},{"key":"2026052110405384700_bib24","doi-asserted-by":"crossref","first-page":"1668","DOI":"10.1177\/0962280219869742","article-title":"Inverse probability weighted Cox model in multi-site studies without sharing individual-level data","volume":"29","author":"Shu","year":"2020","journal-title":"Statistical Methods in Medical Research"},{"key":"2026052110405384700_bib25","doi-asserted-by":"crossref","DOI":"10.1007\/0-387-37119-2","volume-title":"The statistical analysis of interval-censored failure time data","author":"Sun","year":"2006"},{"key":"2026052110405384700_bib26","first-page":"3915","article-title":"Fused lasso approach in regression coefficients clustering-learning parameter heterogeneity in data integration","volume":"17","author":"Tang","year":"2016","journal-title":"Journal of Machine Learning Research"},{"key":"2026052110405384700_bib27","doi-asserted-by":"crossref","first-page":"1039","DOI":"10.1198\/016214507000000509","article-title":"Unified LASSO estimation by least squares approximation","volume":"102","author":"Wang","year":"2007","journal-title":"Journal of the American Statistical Association"},{"key":"2026052110405384700_bib28","doi-asserted-by":"crossref","first-page":"485","DOI":"10.1080\/01621459.2022.2126363","article-title":"Learning coefficient heterogeneity over networks: A Distributed Spanning-Tree-Based Fused-Lasso regression","volume":"119","author":"Zhang","year":"2024","journal-title":"Journal of the American Statistical Association"},{"key":"2026052110405384700_bib29","doi-asserted-by":"crossref","first-page":"1400","DOI":"10.1214\/15-AOS1410","article-title":"A partially linear framework for massive heterogeneous data","volume":"44","author":"Zhao","year":"2016","journal-title":"The Annals of Statistics"},{"key":"2026052110405384700_bib30","doi-asserted-by":"crossref","first-page":"1004","DOI":"10.1080\/10618600.2021.1923517","article-title":"Least-square approximation for a distributed system","volume":"30","author":"Zhu","year":"2021","journal-title":"Journal of Computational and Graphical Statistics"},{"key":"2026052110405384700_bib31","doi-asserted-by":"crossref","first-page":"1418","DOI":"10.1198\/016214506000000735","article-title":"The adaptive lasso and its oracle properties","volume":"101","author":"Zou","year":"2006","journal-title":"Journal of the American Statistical Association"}],"container-title":["Biometrics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/biometrics\/article-pdf\/82\/2\/ujag091\/68357757\/ujag091.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/biometrics\/article-pdf\/82\/2\/ujag091\/68357757\/ujag091.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T14:41:02Z","timestamp":1779374462000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/biometrics\/article\/doi\/10.1093\/biomtc\/ujag091\/8689489"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,9]]},"references-count":31,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4,9]]}},"URL":"https:\/\/doi.org\/10.1093\/biomtc\/ujag091","relation":{},"ISSN":["0006-341X","1541-0420"],"issn-type":[{"value":"0006-341X","type":"print"},{"value":"1541-0420","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,6]]},"published":{"date-parts":[[2026,4,9]]},"article-number":"ujag091"}}