{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T01:26:04Z","timestamp":1773105964325,"version":"3.50.1"},"reference-count":40,"publisher":"Oxford University Press (OUP)","issue":"24","license":[{"start":{"date-parts":[[2020,12,15]],"date-time":"2020-12-15T00:00:00Z","timestamp":1607990400000},"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\/100000050","name":"National Heart, Lung, and Blood Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000050","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000050","name":"NHLBI","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000050","id-type":"DOI","asserted-by":"publisher"}]},{"name":"The Nephrotic Syndrome Study Network Consortium","award":["U54-DK-083912"],"award-info":[{"award-number":["U54-DK-083912"]}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Rare Disease Clinical Research Network"},{"DOI":"10.13039\/100000062","name":"National Institute of Diabetes, Digestive, and Kidney Diseases","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100000062","id-type":"DOI","asserted-by":"crossref"}]},{"name":"NephCure Kidney International"},{"DOI":"10.13039\/100019452","name":"Halpin Foundation","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100019452","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Organ Procurement and Transplantation Network"},{"DOI":"10.13039\/100008269","name":"Michigan Institute for Clinical and Health Research","doi-asserted-by":"publisher","award":["UL1TR002240"],"award-info":[{"award-number":["UL1TR002240"]}],"id":[{"id":"10.13039\/100008269","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,4,5]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Summary<\/jats:title>\n                  <jats:p>Restricted mean survival time (RMST) is a useful summary measurement of the time-to-event data, and it has attracted great attention for its straightforward clinical interpretation. In this article, I propose a deep neural network model that directly relates the RMST to its baseline covariates for simultaneous prediction of RSMT at multiple times. Each subject\u2019s survival time is transformed into a series of jackknife pseudo observations and then used as quantitative response variables in a deep neural network model. By using the pseudo values, a complex survival analysis is reduced to a standard regression problem, which greatly simplifies the neural network construction. By jointly modeling RMST at multiple times, the neural network model gains prediction accuracy by information sharing across times. The proposed network model was evaluated by extensive simulation studies and was further illustrated on three real datasets. In real data analyses, I also used methods to open the blackbox by identifying subject-specific predictors and their importance in contributing to the risk prediction.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>The source code is freely available at http:\/\/github.com\/lilizhaoUM\/DnnRMST.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Supplementary information<\/jats:title>\n                  <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaa1082","type":"journal-article","created":{"date-parts":[[2020,12,17]],"date-time":"2020-12-17T18:53:10Z","timestamp":1608231190000},"page":"5672-5677","source":"Crossref","is-referenced-by-count":9,"title":["Deep neural networks for predicting restricted mean survival times"],"prefix":"10.1093","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6366-8206","authenticated-orcid":false,"given":"Lili","family":"Zhao","sequence":"first","affiliation":[{"name":"Department of Biostatistics, School of Public Health, University of Michigan , Ann Arbor, MI 48105, USA"}]}],"member":"286","published-online":{"date-parts":[[2021,1,5]]},"reference":[{"key":"2023062408144242000_btaa1082-B42","article-title":"TensorFlow: Large-scale machine learning on heterogeneous systems. Software available from tensorflow.org","author":"Abadi","year":"2015"},{"key":"2023062408144242000_btaa1082-B3","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1177\/0962280209105020","article-title":"Pseudo-observations in survival analysis","volume":"19","author":"Andersen","year":"2010","journal-title":"Stat. Methods Med. Res"},{"key":"2023062408144242000_btaa1082-B4","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1093\/biomet\/90.1.15","article-title":"Generalised linear models for correlated pseudo-observations, with applications to multistate models","volume":"90","author":"Andersen","year":"2003","journal-title":"Biometrika"},{"key":"2023062408144242000_btaa1082-B5","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1007\/s10985-004-4771-0","article-title":"Regression analysis of restricted mean survival time based on pseudo-observations","volume":"10","author":"Andersen","year":"2004","journal-title":"Lifetime Data Anal"},{"key":"2023062408144242000_btaa1082-B6","first-page":"281","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"Bergstra","year":"2012","journal-title":"J. Mach. Learn. Res"},{"key":"2023062408144242000_btaa1082-B7","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s10985-013-9247-7","article-title":"Pseudo-observations for competing risks with covariate dependent censoring","volume":"20","author":"Binder","year":"2014","journal-title":"Lifetime Data Anal"},{"key":"2023062408144242000_btaa1082-B8","doi-asserted-by":"crossref","first-page":"1030","DOI":"10.1111\/j.0006-341X.2001.01030.x","article-title":"Causal inference on the difference of the restricted mean lifetime between two groups","volume":"57","author":"Chen","year":"2001","journal-title":"Biometrics"},{"key":"2023062408144242000_btaa1082-B9","doi-asserted-by":"crossref","first-page":"e100607","DOI":"10.1371\/journal.pcbi.1006076","article-title":"Cox-nnet: an artificial neural network method for prognosis prediction of high-throughput omics data","volume":"14","author":"Ching","year":"2018","journal-title":"PLoS Comput. Biol"},{"key":"2023062408144242000_btaa1082-B10","author":"Chollet","year":"2015"},{"key":"2023062408144242000_btaa1082-B11","doi-asserted-by":"crossref","first-page":"397","DOI":"10.1111\/sjos.12112","article-title":"Estimating mean survival time: when is it possible?","volume":"42","author":"Ding","year":"2015","journal-title":"Scand. J. Stat"},{"key":"2023062408144242000_btaa1082-B12","doi-asserted-by":"crossref","first-page":"358","DOI":"10.1016\/1047-2797(93)90062-9","article-title":"Recruitment of adults 65 years and older as participants in the cardiovascular health study","volume":"3","author":"DrPhilos","year":"1993","journal-title":"Ann. Epidemiol"},{"key":"2023062408144242000_btaa1082-B13","doi-asserted-by":"crossref","first-page":"749","DOI":"10.1038\/ki.2012.428","article-title":"Design of the nephrotic syndrome study network (NEPTUNE) to evaluate primary glomerular nephropathy by a multidisciplinary approach","volume":"83","author":"Gadegbeku","year":"2013","journal-title":"Kidney Int"},{"key":"2023062408144242000_btaa1082-B14","doi-asserted-by":"crossref","first-page":"1957","DOI":"10.1002\/sim.8076","article-title":"Evaluating center-specific long-term outcomes through differences in mean survival time: analysis of national kidney transplant data","volume":"38","author":"He","year":"2019","journal-title":"Stat. Med"},{"key":"2023062408144242000_btaa1082-B15","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1111\/j.0006-341X.2005.030814.x","article-title":"Survival model predictive accuracy and roc curves","volume":"61","author":"Heagerty","year":"2005","journal-title":"Biometrics"},{"key":"2023062408144242000_btaa1082-B16","first-page":"841","article-title":"Random survival forests","volume":"2","author":"Ishwaran","year":"2008","journal-title":"Ann. App. Stat"},{"key":"2023062408144242000_btaa1082-B17","doi-asserted-by":"crossref","first-page":"1169","DOI":"10.1080\/01621459.1987.10478555","article-title":"Restricted mean life with adjustment for covariates","volume":"82","author":"Karrison","year":"1987","journal-title":"J. Am. Stat. Assoc"},{"key":"2023062408144242000_btaa1082-B18","first-page":"223","article-title":"Regression modeling of competing risks data based on pseudovalues of the cumulative incidence function","volume":"61","author":"Klein","year":"2005","journal-title":"SIM"},{"key":"2023062408144242000_btaa1082-B19","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1016\/j.cmpb.2007.11.017","article-title":"SAS and R functions to compute pseudo-values for censored data regression","volume":"89","author":"Klein","year":"2008","journal-title":"Comput. Methods Programs Biomed"},{"key":"2023062408144242000_btaa1082-B20","author":"Kotila","year":"2019"},{"key":"2023062408144242000_btaa1082-B21","doi-asserted-by":"crossref","first-page":"1085","DOI":"10.1111\/j.0006-341X.1999.01085.x","article-title":"Sequential methods for comparing years of life saved in the two-sample censored data","volume":"55","author":"Murray","year":"1999","journal-title":"Biometrics"},{"key":"2023062408144242000_btaa1082-B22","doi-asserted-by":"crossref","first-page":"1988","DOI":"10.1214\/16-AOS1516","article-title":"Asymptotic theory of generalized estimating equations based on jack-knife pseudo-observations","volume":"45","author":"Overgaard","year":"2017","journal-title":"Ann. Stat"},{"key":"2023062408144242000_btaa1082-B23","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1016\/j.jspi.2019.02.003","article-title":"Pseudo-observations under covariate-dependent censoring","volume":"202","author":"Overgaard","year":"2019","journal-title":"J. Stat. Plan. Inference"},{"key":"2023062408144242000_btaa1082-B24","author":"Pedersen","year":"2018"},{"key":"2023062408144242000_btaa1082-B25","article-title":"\u201cwhy should i trust you?\u201d: explaining the predictions of any classifier","author":"Ribeiro","year":"2016","journal-title":"arXiv: 1602.04938"},{"key":"2023062408144242000_btaa1082-B26","doi-asserted-by":"crossref","first-page":"2409","DOI":"10.1002\/sim.4274","article-title":"The use of restricted mean survival time to estimate the treatment effect in randomized clinical trials when the proportional hazards assumption is in doubt","volume":"30","author":"Royston","year":"2011","journal-title":"Stat. Med"},{"key":"2023062408144242000_btaa1082-B27","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1111\/j.1541-0420.2010.01449.x","article-title":"Double inverse-weighted estimation of cumulative treatment effects under nonproportional hazards and dependent censoring","volume":"67","author":"Schaubel","year":"2011","journal-title":"Biometrics"},{"key":"2023062408144242000_btaa1082-B28","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res"},{"key":"2023062408144242000_btaa1082-B29","doi-asserted-by":"crossref","first-page":"2339","DOI":"10.1002\/sim.8542","article-title":"Deep learning for survival outcomes","volume":"39","author":"Steingrimsson","year":"2020","journal-title":"Stat. Med"},{"key":"2023062408144242000_btaa1082-B30","doi-asserted-by":"crossref","first-page":"2435","DOI":"10.1002\/sim.7283","article-title":"Statistical consequences of a successful lung allocation system \u2013 recovering information and reducing bias in models for urgency","volume":"36","author":"Tayob","year":"2017","journal-title":"Stat. Med"},{"key":"2023062408144242000_btaa1082-B31","doi-asserted-by":"crossref","first-page":"222","DOI":"10.1093\/biostatistics\/kxt050","article-title":"Predicting the restricted mean event time with the subject\u2019s baseline covariates in survival analysis","volume":"15","author":"Tian","year":"2014","journal-title":"Biostatistics"},{"key":"2023062408144242000_btaa1082-B32","doi-asserted-by":"crossref","first-page":"2380","DOI":"10.1200\/JCO.2014.55.2208","article-title":"Moving beyond the hazard ratio in quantifying the between-group difference in survival analysis","volume":"32","author":"Uno","year":"2014","journal-title":"J. Clin. Oncol"},{"key":"2023062408144242000_btaa1082-B33","doi-asserted-by":"crossref","first-page":"176","DOI":"10.1007\/s10985-017-9391-6","article-title":"Modeling restricted mean survival time under general censoring mechanisms","volume":"24","author":"Wang","year":"2018","journal-title":"Lifetime Data Anal"},{"key":"2023062408144242000_btaa1082-B34","doi-asserted-by":"crossref","first-page":"561","DOI":"10.1002\/sim.4450","article-title":"Restricted mean models for transplant benefit and urgency","volume":"31","author":"Xiang","year":"2012","journal-title":"Stat. Med"},{"key":"2023062408144242000_btaa1082-B35","doi-asserted-by":"crossref","first-page":"740","DOI":"10.1111\/j.1541-0420.2010.01503.x","article-title":"Estimating differences in restricted mean lifetime using observational data subject to dependent censoring","volume":"67","author":"Zhang","year":"2011","journal-title":"Biometrics"},{"key":"2023062408144242000_btaa1082-B36","doi-asserted-by":"crossref","first-page":"1101","DOI":"10.1111\/j.0006-341X.1999.01101.x","article-title":"Efficient estimation of the distribution of quality-adjusted survival time","volume":"55","author":"Zhao","year":"1999","journal-title":"Biometrics"},{"key":"2023062408144242000_btaa1082-B37","doi-asserted-by":"crossref","first-page":"3308","DOI":"10.1109\/JBHI.2020.2980204","article-title":"Deep neural networks for survival analysis using pseudo values","volume":"24","author":"Zhao","year":"2020","journal-title":"IEEE J. Biomed. Health Inf"},{"key":"2023062408144242000_btaa1082-B38","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1111\/biom.12384","article-title":"On the restricted mean survival time curve in survival analysis","volume":"72","author":"Zhao","year":"2016","journal-title":"Biometrics"},{"key":"2023062408144242000_btaa1082-B39","doi-asserted-by":"crossref","first-page":"3685","DOI":"10.1002\/sim.8687","article-title":"Incorporating longitudinal biomarkers for dynamic risk prediction in the era of big data: a pseudo-observation approach","volume":"39","author":"Zhao","year":"2020","journal-title":"Stat. Med"},{"key":"2023062408144242000_btaa1082-B40","author":"Zhong","year":"2020"},{"key":"2023062408144242000_btaa1082-B41","doi-asserted-by":"crossref","first-page":"702","DOI":"10.1080\/01621459.1998.10473722","article-title":"Restricted mean life with covariates: modification and extension of a useful survival analysis method","volume":"93","author":"Zucker","year":"1998","journal-title":"J. Am. Stat. Assoc"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaa1082\/35407093\/btaa1082.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/36\/24\/5672\/50693060\/btaa1082.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/36\/24\/5672\/50693060\/btaa1082.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,24]],"date-time":"2023-06-24T23:46:42Z","timestamp":1687650402000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/36\/24\/5672\/6064143"}},"subtitle":[],"editor":[{"given":"Lenore","family":"Cowen","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2020,12,15]]},"references-count":40,"journal-issue":{"issue":"24","published-print":{"date-parts":[[2021,4,5]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaa1082","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2020,12,15]]},"published":{"date-parts":[[2020,12,15]]}}}