{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T14:43:46Z","timestamp":1792593826798,"version":"4.5.0"},"reference-count":37,"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"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["1R01HL175410"],"award-info":[{"award-number":["1R01HL175410"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"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>In survival analysis, integrating multiple data sources holds significant potential to increase event counts, improve statistical efficiency, and enhance scientific discovery. However, challenges arise when external datasets differ in data forms, distributions, and covariate availability. We propose a novel learning framework that strengthens statistical inference of internal Cox regression coefficients through efficient data integration. Our framework is robust integration and accommodates multifaceted data heterogeneity through transformation, working models, penalized approach, and weighting that adaptively selects homogeneous components. The resulting estimators are consistent, asymptotically normal, more efficient than internal-only estimators, and robust to working model misspecification and data heterogeneity. Simulation studies confirm our framework\u2019s favorable properties. We applied our method to study dementia risk among black individuals in the Religious Orders Study and the Rush Memory and Aging Project, integrating information from external cohorts, including the Alzheimer\u2019s Disease Neuroimaging Initiative and the National Alzheimer\u2019s Coordinating Center. The analysis identified key risk factors with improved efficiency and demonstrated clinical relevance.<\/jats:p>","DOI":"10.1093\/biostatistics\/kxag035","type":"journal-article","created":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T11:39:36Z","timestamp":1787657976000},"source":"Crossref","is-referenced-by-count":0,"title":["A data integration framework to improve the efficiency of survival analysis by leveraging multiple external studies with multifaceted heterogeneity"],"prefix":"10.1093","volume":"27","author":[{"given":"Daxuan","family":"Deng","sequence":"first","affiliation":[{"name":"Division of Biostatistics and Bioinformatics, Department of Public Health Sciences, Penn State College of Medicine , 700 HMC Cres Road , Hershey, PA 17033,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5474-2833","authenticated-orcid":false,"given":"Chixiang","family":"Chen","sequence":"additional","affiliation":[{"name":"Division of Biostatistics and Bioinformatics, Department of Epidemiology and Public Health, University of Maryland School of Medicine, 685 West Baltimore Street, Baltimore, MD 21201,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lijun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Population and Quantitative Health Sciences, Case Western Reserve University School of Medicine, 10900 Euclid Avenue, Cleveland, OH 44016,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vernon M","family":"Chinchilli","sequence":"additional","affiliation":[{"name":"Division of Biostatistics and Bioinformatics, Department of Public Health Sciences, Penn State College of Medicine , 700 HMC Cres Road , Hershey, PA 17033,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9977-7041","authenticated-orcid":false,"given":"Ming","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Population and Quantitative Health Sciences, Case Western Reserve University School of Medicine, 10900 Euclid Avenue, Cleveland, OH 44016,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,10,7]]},"reference":[{"key":"2026102110223577600_kxag035-B1","doi-asserted-by":"publisher","first-page":"580","DOI":"10.1377\/hlthaff.2013.1353","article-title":"Alzheimer\u2019s disease in African Americans: risk factors and challenges for the future","volume":"33","author":"Barnes","year":"2014","journal-title":"Health Aff (Millwood)"},{"key":"2026102110223577600_kxag035-B2","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1177\/0164027511434086","article-title":"Education and dementia risk: results from the aging demographics and memory study","volume":"35","author":"Basu","year":"2013","journal-title":"Res Aging"},{"key":"2026102110223577600_kxag035-B3","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1097\/WAD.0b013e318142774e","article-title":"The national Alzheimer\u2019s coordinating center (NACC) database: the uniform data set","volume":"21","author":"Beekly","year":"2007","journal-title":"Alzheimer Dis Assoc Disorders"},{"key":"2026102110223577600_kxag035-B4","doi-asserted-by":"publisher","first-page":"S161","DOI":"10.3233\/JAD-179939","article-title":"Religious orders study and rush memory and aging project","volume":"64","author":"Bennett","year":"2018","journal-title":"J Alzheimers Dis"},{"key":"2026102110223577600_kxag035-B5","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1007\/s10985-014-9317-5","article-title":"Z-estimation and stratified samples: application to survival models","volume":"21","author":"Breslow","year":"2015","journal-title":"Lifetime Data Anal"},{"key":"2026102110223577600_kxag035-B6","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1080\/01621459.2015.1123157","article-title":"Constrained maximum likelihood estimation for model calibration using summary-level information from external big data sources","volume":"111","author":"Chatterjee","year":"2016","journal-title":"J Am Stat Assoc"},{"key":"2026102110223577600_kxag035-B7","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2025.2542553","article-title":"The effect of alcohol intake on brain white matter microstructural integrity: a new causal inference framework for incomplete phenomic data","author":"Chen","year":"2025","journal-title":"J Am Stat Assoc"},{"key":"2026102110223577600_kxag035-B8","doi-asserted-by":"publisher","first-page":"ujae090","DOI":"10.1093\/biomtc\/ujae090","article-title":"Integrating external summary information in the presence of prior probability shift: an application to assessing essential hypertension","volume":"80","author":"Chen","year":"2024","journal-title":"Biometrics"},{"key":"2026102110223577600_kxag035-B9","doi-asserted-by":"publisher","first-page":"2947","DOI":"10.1111\/biom.13858","article-title":"An efficient data integration scheme for synthesizing information from multiple secondary datasets for the parameter inference of the main analysis","volume":"79","author":"Chen","year":"2023","journal-title":"Biometrics"},{"key":"2026102110223577600_kxag035-B10","doi-asserted-by":"publisher","first-page":"2100326","DOI":"10.1002\/bimj.202100326","article-title":"Synthesizing secondary data into survival analysis to improve estimation efficiency","volume":"65","author":"Chen","year":"2023","journal-title":"Biometrical J"},{"key":"2026102110223577600_kxag035-B11","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1016\/j.trci.2018.08.009","article-title":"Racial and ethnic differences in trends in dementia prevalence and risk factors in the United States","volume":"4","author":"Chen","year":"2018","journal-title":"Alzheimers Dement (N Y))"},{"key":"2026102110223577600_kxag035-B12","doi-asserted-by":"publisher","first-page":"754","DOI":"10.1016\/S0929-6646(09)60402-2","article-title":"Risk factors for dementia","volume":"108","author":"Chen","year":"2009","journal-title":"J Formos Med Assoc"},{"key":"2026102110223577600_kxag035-B13","doi-asserted-by":"publisher","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":"2026102110223577600_kxag035-B14","doi-asserted-by":"publisher","first-page":"1249","DOI":"10.1177\/09622802241254195","article-title":"Robust integration of secondary outcomes information into primary outcome analysis in the presence of missing data","volume":"33","author":"Deng","year":"2024","journal-title":"Stat Methods Med Res"},{"key":"2026102110223577600_kxag035-B15","doi-asserted-by":"publisher","first-page":"qkaf081","DOI":"10.1093\/jrsssb\/qkaf081","article-title":"A new integrative learning framework for integrating multiple secondary outcomes into primary outcome analysis: a case study on liver health","author":"Deng","year":"2025","journal-title":"J R Stat Soc Ser B Stat Methodol"},{"key":"2026102110223577600_kxag035-B16","doi-asserted-by":"publisher","first-page":"ujae168","DOI":"10.1093\/biomtc\/ujae168","article-title":"Improving estimation efficiency for survival data analysis by integrating a coarsened time-to-event outcome from an external study","volume":"81","author":"Deng","year":"2025","journal-title":"Biometrics"},{"key":"2026102110223577600_kxag035-B17","doi-asserted-by":"publisher","first-page":"1348","DOI":"10.1198\/016214501753382273","article-title":"Variable selection via nonconcave penalized likelihood and its oracle properties","volume":"96","author":"Fan","year":"2001","journal-title":"J Am Stat Assoc"},{"key":"2026102110223577600_kxag035-B18","doi-asserted-by":"publisher","first-page":"496","DOI":"10.1080\/01621459.1999.10474144","article-title":"A proportional hazards model for the subdistribution of a competing risk","volume":"94","author":"Fine","year":"1999","journal-title":"J Am Stat Assoc"},{"key":"2026102110223577600_kxag035-B19","doi-asserted-by":"publisher","first-page":"723","DOI":"10.1093\/jrsssb\/qkae111","article-title":"Robust angle-based transfer learning in high dimensions","volume":"87","author":"Gu","year":"2025","journal-title":"J R Stat Soc Series B Stat Methodol"},{"key":"2026102110223577600_kxag035-B20","doi-asserted-by":"publisher","DOI":"10.1093\/biomtc\/ujae072","article-title":"Improving prediction of linear regression models by integrating external information from heterogeneous populations: James\u2013stein estimators","volume":"80","author":"Han","year":"2024","journal-title":"Biometrics"},{"key":"2026102110223577600_kxag035-B21","doi-asserted-by":"publisher","first-page":"787","DOI":"10.1080\/01621459.2015.1044090","article-title":"Efficient estimation of the cox model with auxiliary subgroup survival information","volume":"111","author":"Huang","year":"2016","journal-title":"J Am Stat Assoc"},{"key":"2026102110223577600_kxag035-B22","doi-asserted-by":"publisher","first-page":"5630","DOI":"10.1002\/sim.9929","article-title":"Simultaneous selection and incorporation of consistent external aggregate information","volume":"42","author":"Huang","year":"2023","journal-title":"Stat Med"},{"key":"2026102110223577600_kxag035-B23","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1002\/jmri.21049","article-title":"The Alzheimer\u2019s disease neuroimaging initiative (ADNI): MRI methods","volume":"27","author":"Jack","year":"2008","journal-title":"J Magn Reson Imaging"},{"key":"2026102110223577600_kxag035-B24","volume-title":"The statistical analysis of failure time data","author":"Kalbfleisch","year":"2011"},{"key":"2026102110223577600_kxag035-B25","doi-asserted-by":"publisher","first-page":"703","DOI":"10.1093\/biomet\/ass014","article-title":"Penalized empirical likelihood and growing dimensional general estimating equations","volume":"99","author":"Leng","year":"2012","journal-title":"Biometrika"},{"key":"2026102110223577600_kxag035-B26","doi-asserted-by":"publisher","first-page":"1274","DOI":"10.1080\/01621459.2023.2184373","article-title":"Estimation and inference for high-dimensional generalized linear models with knowledge transfer","volume":"119","author":"Li","year":"2024","journal-title":"J Am Stat Assoc"},{"key":"2026102110223577600_kxag035-B27","doi-asserted-by":"publisher","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":"2026102110223577600_kxag035-B28","doi-asserted-by":"publisher","first-page":"1074","DOI":"10.1080\/01621459.1989.10478874","article-title":"The robust inference for the cox proportional hazards model","volume":"84","author":"Lin","year":"1989","journal-title":"J Am Stat Assoc"},{"key":"2026102110223577600_kxag035-B29","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1093\/biomet\/81.1.61","article-title":"Semiparametric analysis of the additive risk model","volume":"81","author":"Lin","year":"1994","journal-title":"Biometrika"},{"key":"2026102110223577600_kxag035-B30","doi-asserted-by":"publisher","DOI":"10.1093\/biostatistics\/kxag011","article-title":"Adaptive transfer learning for time-to-event modeling with applications in disease risk assessment [preprint]","author":"Lu","year":"2026"},{"key":"2026102110223577600_kxag035-B31","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1177\/0891988708328220","article-title":"Parental education and late-life dementia in the United States","volume":"22","author":"Rogers","year":"2009","journal-title":"J Geriatr Psychiatry Neurol"},{"key":"2026102110223577600_kxag035-B32","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1111\/j.1747-4949.2011.00731.x","article-title":"Dementia, stroke, and vascular risk factors; a review","volume":"7","author":"Sahathevan","year":"2012","journal-title":"Int J Stroke"},{"key":"2026102110223577600_kxag035-B33","volume-title":"Asymptotic statistics","author":"Van der Vaart","year":"2000"},{"key":"2026102110223577600_kxag035-B34","doi-asserted-by":"publisher","first-page":"323","DOI":"10.3233\/JAD-220207","article-title":"Diabetes, hypertension, and the risk of dementia","volume":"89","author":"Yen","year":"2022","journal-title":"J Alzheimers Dis"},{"key":"2026102110223577600_kxag035-B35","doi-asserted-by":"publisher","first-page":"894","DOI":"10.1214\/09-AOS729","article-title":"Nearly unbiased variable selection under minimax concave penalty","volume":"38","author":"Zhang","year":"2010","journal-title":"Ann Statist"},{"key":"2026102110223577600_kxag035-B36","doi-asserted-by":"publisher","first-page":"689","DOI":"10.1093\/biomet\/asaa014","article-title":"Generalized integration model for improved statistical inference by leveraging external summary data","volume":"107","author":"Zhang","year":"2020","journal-title":"Biometrika"},{"key":"2026102110223577600_kxag035-B37","doi-asserted-by":"publisher","first-page":"1418","DOI":"10.1198\/016214506000000735","article-title":"The adaptive lasso and its oracle properties","volume":"101","author":"Zou","year":"2006","journal-title":"J Am Stat Assoc"}],"container-title":["Biostatistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/biostatistics\/article-pdf\/27\/1\/kxag035\/71668597\/kxag035.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/biostatistics\/article-pdf\/27\/1\/kxag035\/71668597\/kxag035.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T14:22:42Z","timestamp":1792592562000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/biostatistics\/article\/doi\/10.1093\/biostatistics\/kxag035\/8876145"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":37,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,1,20]]}},"URL":"https:\/\/doi.org\/10.1093\/biostatistics\/kxag035","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":"kxag035"}}