{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T18:40:43Z","timestamp":1793126443057,"version":"4.5.0"},"reference-count":41,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,1,20]]},"abstract":"<jats:title>Summary<\/jats:title>\n                  <jats:p>To address the challenges in modeling time-to-event outcomes in small-sample settings, we propose a novel transfer learning approach, termed CoxTL, based on the widely used Cox proportional hazards model, accounting for potential covariate and concept shifts between source and target datasets. CoxTL utilizes a combination of density ratio weighting and importance weighting techniques to address multi-level data heterogeneity, including covariate and coefficient shifts between source and target datasets. Additionally, it accounts for potential model misspecification, ensuring robustness across a wide range of settings. We assess the performance of CoxTL through extensive simulation studies, considering data under various types of distributional shifts. In addition, we apply CoxTL to predict End-Stage Renal Disease (ESRD) in the Hispanic population using electronic health record-derived features from the All of Us Research Program. Data from non-Hispanic White and non-Hispanic Black populations are leveraged as source cohorts. Model performance is evaluated using the C-index and Integrated Brier Score (IBS). In simulation studies, CoxTL demonstrates higher predictive accuracy, particularly in scenarios involving multi-level heterogeneity between target and source datasets. In other scenarios, CoxTL performs comparably to alternative methods specifically designed to address only a single type of distributional shift. For predicting the 2-year risk of ESRD in the Hispanic population, CoxTL achieves an increase in the C-index of up to 6.76% compared to the model trained exclusively on target data. Furthermore, it demonstrates up to a 17.94% increase in the C-index compared to the state-of-the-art transfer learning method based on Cox model. The proposed method effectively utilizes source data to enhance time-to-event predictions in target populations with limited samples. Its ability to handle various sources and levels of data heterogeneity ensures robustness, making it particularly well-suited for real-world applications involving target populations with small sample sizes, where traditional Cox models often struggle.<\/jats:p>","DOI":"10.1093\/biostatistics\/kxag011","type":"journal-article","created":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T11:40:41Z","timestamp":1775821241000},"source":"Crossref","is-referenced-by-count":4,"title":["Adaptive transfer learning for time-to-event modeling with applications in disease risk assessment"],"prefix":"10.1093","volume":"27","author":[{"given":"Yuying","family":"Lu","sequence":"first","affiliation":[{"name":"Department of Biostatistic, Columbia Mailman School of Public Health, 722 W 168th St, New York City, New York 10032,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0856-8843","authenticated-orcid":false,"given":"Tian","family":"Gu","sequence":"additional","affiliation":[{"name":"Department of Biostatistic, Columbia Mailman School of Public Health, 722 W 168th St, New York City, New York 10032,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9261-4864","authenticated-orcid":false,"given":"Rui","family":"Duan","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, Harvard T.H. Chan School of Public Health, 655 Huntington Ave, Boston, MA 02115,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,5,31]]},"reference":[{"key":"2026102110230382700_kxag011-B1","first-page":"1736"},{"key":"2026102110230382700_kxag011-B2","doi-asserted-by":"crossref","first-page":"8683","DOI":"10.1021\/acs.jmedchem.9b02147","article-title":"Transfer learning for drug discovery","volume":"63","author":"Cai","year":"2020","journal-title":"J Med Chem"},{"key":"2026102110230382700_kxag011-B3","doi-asserted-by":"crossref","first-page":"ujae120","DOI":"10.1093\/biomtc\/ujae120","article-title":"Likelihood adaptively incorporated external aggregate information with uncertainty for survival data","volume":"80","author":"Chen","year":"2024","journal-title":"Biometrics"},{"key":"2026102110230382700_kxag011-B4","first-page":"172"},{"key":"2026102110230382700_kxag011-B5","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":"J R Stat Soc Ser B (Methodol)"},{"key":"2026102110230382700_kxag011-B6"},{"key":"2026102110230382700_kxag011-B7","doi-asserted-by":"crossref","first-page":"508","DOI":"10.1214\/aos\/1032894451","article-title":"Density estimation by wavelet thresholding","volume":"24","author":"Donoho","year":"1996","journal-title":"Ann Stat"},{"key":"2026102110230382700_kxag011-B8","doi-asserted-by":"crossref","first-page":"362","DOI":"10.1214\/aos\/1176344130","article-title":"The geometry of exponential families","volume":"6","author":"Efron","year":"1978","journal-title":"Ann Stat"},{"key":"2026102110230382700_kxag011-B9","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1186\/s12889-024-17721-9","article-title":"Critical analyses of Latina mortality: disentangling the heterogeneity of ethnic origin, place, nativity, race, and socioeconomic status","volume":"24","author":"Errisuriz","year":"2024","journal-title":"BMC Public Health"},{"key":"2026102110230382700_kxag011-B10","doi-asserted-by":"crossref","first-page":"1525","DOI":"10.1038\/s42256-024-00932-5","article-title":"Stable cox regression for survival analysis under distribution shifts","volume":"6","author":"Fan","year":"2024","journal-title":"Nat Mach Intell"},{"key":"2026102110230382700_kxag011-B11","doi-asserted-by":"crossref","first-page":"igz017","DOI":"10.1093\/geroni\/igz017","article-title":"Biological risk profiles among Latino subgroups in the health and retirement study","volume":"3","author":"Garc\u00eda","year":"2019","journal-title":"Innov Aging"},{"key":"2026102110230382700_kxag011-B12","doi-asserted-by":"crossref","first-page":"572","DOI":"10.1093\/biomet\/88.2.572","article-title":"On functional misspecification of covariates in the cox regression model","volume":"88","author":"Gerds","year":"2001","journal-title":"Biometrika"},{"key":"2026102110230382700_kxag011-B13","doi-asserted-by":"crossref","first-page":"2529","DOI":"10.1002\/(SICI)1097-0258(19990915\/30)18:17\/18<2529::AID-SIM274>3.0.CO;2-5","article-title":"Assessment and comparison of prognostic classification schemes for survival data","volume":"18","author":"Graf","year":"1999","journal-title":"Stat Med"},{"key":"2026102110230382700_kxag011-B15","doi-asserted-by":"publisher","DOI":"10.1093\/jrsssb\/qkae111"},{"key":"2026102110230382700_kxag011-B16","doi-asserted-by":"crossref","first-page":"104243","DOI":"10.1016\/j.jbi.2022.104243","article-title":"Commute: communication-efficient transfer learning for multi-site risk prediction","volume":"137","author":"Gu","year":"2023","journal-title":"J Biomed Inform"},{"key":"2026102110230382700_kxag011-B17","doi-asserted-by":"crossref","first-page":"40","DOI":"10.3174\/ajnr.A6365","article-title":"Deep transfer learning and radiomics feature prediction of survival of patients with high-grade gliomas","volume":"41","author":"Han","year":"2020","journal-title":"Am J Neuroradiol"},{"key":"2026102110230382700_kxag011-B18","first-page":"249"},{"key":"2026102110230382700_kxag011-B19","doi-asserted-by":"crossref","first-page":"12004","DOI":"10.1073\/pnas.1920913117","article-title":"Catalytic prior distributions with application to generalized linear models","volume":"117","author":"Huang","year":"2020","journal-title":"Proc Natl Acad Sci USA"},{"key":"2026102110230382700_kxag011-B20","doi-asserted-by":"crossref","first-page":"10353","DOI":"10.1038\/s41598-017-10649-8","article-title":"A deep learning-based radiomics model for prediction of survival in glioblastoma multiforme","volume":"7","author":"Lao","year":"2017","journal-title":"Sci Rep"},{"key":"2026102110230382700_kxag011-B21","doi-asserted-by":"crossref","first-page":"604","DOI":"10.7326\/0003-4819-150-9-200905050-00006","article-title":"A new equation to estimate glomerular filtration rate","volume":"150","author":"Levey","year":"2009","journal-title":"Ann Intern Med"},{"key":"2026102110230382700_kxag011-B22","doi-asserted-by":"crossref","first-page":"776","DOI":"10.1093\/biostatistics\/kxac006","article-title":"Distributed cox proportional hazards regression using summary-level information","volume":"24","author":"Li","year":"2023","journal-title":"Biostatistics"},{"key":"2026102110230382700_kxag011-B23","author":"Li","year":"2024"},{"key":"2026102110230382700_kxag011-B24","author":"Li","year":"2023"},{"key":"2026102110230382700_kxag011-B25","first-page":"231","author":"Li","year":"2016"},{"key":"2026102110230382700_kxag011-B26","doi-asserted-by":"crossref","first-page":"2276","DOI":"10.1080\/01621459.2023.2210336","article-title":"Accommodating time-varying heterogeneity in risk estimation under the cox model: a transfer learning approach","volume":"118","author":"Li","year":"2023","journal-title":"J Am Stat Assoc"},{"key":"2026102110230382700_kxag011-B27","doi-asserted-by":"crossref","first-page":"e2101344118","DOI":"10.1073\/pnas.2101344118","article-title":"Density estimation using deep generative neural networks","volume":"118","author":"Liu","year":"2021","journal-title":"Proc Natl Acad Sci USA"},{"key":"2026102110230382700_kxag011-B28","doi-asserted-by":"crossref","first-page":"e0230536","DOI":"10.1371\/journal.pone.0230536","article-title":"Transfer learning with convolutional neural networks for cancer survival prediction using gene-expression data","volume":"15","author":"Lopez-Garcia","year":"2020","journal-title":"PloS One"},{"key":"2026102110230382700_kxag011-B29","first-page":"466","article-title":"Chronic kidney disease in United States Hispanics: a growing public health problem","volume":"19","author":"Lora","year":"2009","journal-title":"Ethn Dis"},{"key":"2026102110230382700_kxag011-B30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s12561-024-09449-2","article-title":"Enhancing genetic risk prediction through federated semi-supervised transfer learning with inaccurate electronic health record data","author":"Lu","year":"2024","journal-title":"Stat Biosci"},{"key":"2026102110230382700_kxag011-B31","doi-asserted-by":"crossref","first-page":"543","DOI":"10.1007\/s12687-023-00686-4","article-title":"Genetic risk prediction in Hispanics\/Latinos: milestones, challenges, and social-ethical considerations","volume":"14","author":"Maldonado","year":"2023","journal-title":"J Community Genet"},{"key":"2026102110230382700_kxag011-B32","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1109\/TAI.2021.3054609","article-title":"A decade survey of transfer learning (2010\u20132020)","volume":"1","author":"Niu","year":"2020","journal-title":"IEEE Trans Artif Intell"},{"key":"2026102110230382700_kxag011-B33","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","article-title":"A survey on transfer learning","volume":"22","author":"Pan","year":"2010","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"2026102110230382700_kxag011-B34","doi-asserted-by":"crossref","first-page":"1773","DOI":"10.1093\/ndt\/gft063","article-title":"Validation of the kidney failure risk equation in European CKD patients","volume":"28","author":"Peeters","year":"2013","journal-title":"Nephrol Dial Transplant"},{"key":"2026102110230382700_kxag011-B35","doi-asserted-by":"crossref","first-page":"115175","DOI":"10.1016\/j.psychres.2023.115175","article-title":"An efficient landmark model for prediction of suicide attempts in multiple clinical settings","volume":"323","author":"Sheu","year":"2023","journal-title":"Psychiatry Res"},{"key":"2026102110230382700_kxag011-B36","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9781139035613","volume-title":"Density ratio estimation in machine learning","author":"Sugiyama","year":"2012"},{"key":"2026102110230382700_kxag011-B37","author":"Tian","year":"2022"},{"key":"2026102110230382700_kxag011-B38","doi-asserted-by":"crossref","first-page":"2684","DOI":"10.1080\/01621459.2022.2071278","article-title":"Transfer learning under high-dimensional generalized linear models","volume":"118","author":"Tian","year":"2023","journal-title":"J Am Stat Assoc"},{"key":"2026102110230382700_kxag011-B39","doi-asserted-by":"crossref","first-page":"1280","DOI":"10.1111\/biom.13685","article-title":"A cross-validation statistical framework for asymmetric data integration","volume":"79","author":"Tran","year":"2023","journal-title":"Biometrics"},{"key":"2026102110230382700_kxag011-B40"},{"key":"2026102110230382700_kxag011-B41","doi-asserted-by":"crossref","first-page":"1238","DOI":"10.1016\/S0140-6736(16)32064-5","article-title":"Chronic kidney disease","volume":"389","author":"Webster","year":"2017","journal-title":"Lancet"},{"key":"2026102110230382700_kxag011-B42","doi-asserted-by":"crossref","first-page":"1998","DOI":"10.1016\/j.ajhg.2022.09.010","article-title":"The construction of cross-population polygenic risk scores using transfer learning","volume":"109","author":"Zhao","year":"2022","journal-title":"Am J Hum Genet"}],"container-title":["Biostatistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/biostatistics\/article-pdf\/27\/1\/kxag011\/68456282\/kxag011.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/biostatistics\/article-pdf\/27\/1\/kxag011\/68456282\/kxag011.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T14:23:15Z","timestamp":1792592595000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/biostatistics\/article\/doi\/10.1093\/biostatistics\/kxag011\/8700196"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":41,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1,20]]}},"URL":"https:\/\/doi.org\/10.1093\/biostatistics\/kxag011","relation":{},"ISSN":["1465-4644","1468-4357"],"issn-type":[{"value":"1465-4644","type":"print"},{"value":"1468-4357","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,1]]},"published":{"date-parts":[[2026,1]]},"article-number":"kxag011"}}