{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T19:32:37Z","timestamp":1785785557202,"version":"3.56.0"},"reference-count":46,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2024,10,11]],"date-time":"2024-10-11T00:00:00Z","timestamp":1728604800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000057","name":"NIGMS","doi-asserted-by":"publisher","award":["R01GM14107"],"award-info":[{"award-number":["R01GM14107"]}],"id":[{"id":"10.13039\/100000057","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000053","name":"NEI","doi-asserted-by":"publisher","award":["R21EY030488"],"award-info":[{"award-number":["R21EY030488"]}],"id":[{"id":"10.13039\/100000053","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000053","name":"NEI","doi-asserted-by":"publisher","award":["S10OD028483"],"award-info":[{"award-number":["S10OD028483"]}],"id":[{"id":"10.13039\/100000053","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,1,13]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>The aim of dynamic prediction is to provide individualized risk predictions over time, which are updated as new data become available. In pursuit of constructing a dynamic prediction model for a progressive eye disorder, age-related macular degeneration (AMD), we propose a time-dependent Cox survival neural network (tdCoxSNN) to predict its progression using longitudinal fundus images. tdCoxSNN builds upon the time-dependent Cox model by utilizing a neural network to capture the nonlinear effect of time-dependent covariates on the survival outcome. Moreover, by concurrently integrating a convolutional neural network with the survival network, tdCoxSNN can directly take longitudinal images as input. We evaluate and compare our proposed method with joint modelling and landmarking approaches through extensive simulations. We applied the proposed approach to two real datasets. One is a large AMD study, the Age-Related Eye Disease Study, in which more than 50,000 fundus images were captured over a period of 12 years for more than 4,000 participants. Another is a public dataset of the primary biliary cirrhosis disease, where multiple laboratory tests were longitudinally collected to predict the time-to-liver transplant. Our approach demonstrates commendable predictive performance in both simulation studies and the analysis of the two real datasets.<\/jats:p>","DOI":"10.1093\/jrsssc\/qlae051","type":"journal-article","created":{"date-parts":[[2024,10,11]],"date-time":"2024-10-11T10:35:49Z","timestamp":1728642949000},"page":"187-203","source":"Crossref","is-referenced-by-count":8,"title":["tdCoxSNN: Time-dependent Cox survival neural network for continuous-time dynamic prediction"],"prefix":"10.1093","volume":"74","author":[{"given":"Lang","family":"Zeng","sequence":"first","affiliation":[{"name":"Department of Biostatistics and Health Data Science, School of Public Health, University of Pittsburgh , Pittsburgh, PA ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jipeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Biostatistics and Health Data Science, School of Public Health, University of Pittsburgh , Pittsburgh, PA ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7196-8703","authenticated-orcid":false,"given":"Wei","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Biostatistics and Health Data Science, School of Public Health, University of Pittsburgh , Pittsburgh, PA ,","place":["USA"]},{"name":"Department of Pediatrics, School of Medicine, University of Pittsburgh , Pittsburgh, PA ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1352-1000","authenticated-orcid":false,"given":"Ying","family":"Ding","sequence":"additional","affiliation":[{"name":"Department of Biostatistics and Health Data Science, School of Public Health, University of Pittsburgh , Pittsburgh, PA ,","place":["USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,10,11]]},"reference":[{"key":"2025011223511922900_qlae051-B1","volume-title":"12th USENIX symposium on operating systems design and implementation (OSDI 16) (pp. 265\u2013283)","author":"Abadi","year":"2016"},{"key":"2025011223511922900_qlae051-B2","author":"Allaire","year":"2019"},{"issue":"1","key":"2025011223511922900_qlae051-B3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12874-019-0873-y","article-title":"Joint model robustness compared with the time-varying covariate Cox model to evaluate the association between a longitudinal marker and a time-to-event endpoint","volume":"19","author":"Arisido","year":"2019","journal-title":"BMC Medical Research Methodology"},{"issue":"4","key":"2025011223511922900_qlae051-B4","doi-asserted-by":"publisher","first-page":"e1006076","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 Computational Biology"},{"issue":"12","key":"2025011223511922900_qlae051-B5","doi-asserted-by":"publisher","first-page":"2331","DOI":"10.1177\/09622802231206477","article-title":"Random survival forests with multivariate longitudinal endogenous covariates","volume":"32","author":"Devaux","year":"2023","journal-title":"Statistical Methods in Medical Research"},{"key":"2025011223511922900_qlae051-B6","doi-asserted-by":"publisher","first-page":"557","DOI":"10.1080\/01621459.1977.10480613","article-title":"The efficiency of Cox\u2019s likelihood function for censored data","volume":"72","author":"Efron","year":"1977","journal-title":"Journal of the American Statistical Association"},{"key":"2025011223511922900_qlae051-B7","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1146\/publhealth.1999.20.issue-1","article-title":"Time-dependent covariates in the Cox proportional-hazards regression model","volume":"20","author":"Fisher","year":"1999","journal-title":"Annual Review of Public Health"},{"key":"2025011223511922900_qlae051-B8","volume-title":"Counting processes and survival analysis","author":"Fleming","year":"2011"},{"key":"2025011223511922900_qlae051-B9","doi-asserted-by":"publisher","first-page":"1029","DOI":"10.1002\/bimj.v48:6","article-title":"Consistent estimation of the expected brier score in general survival models with right-censored event times","volume":"48","author":"Gerds","year":"2006","journal-title":"Biometrical Journal"},{"key":"2025011223511922900_qlae051-B10","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"He","year":"2016"},{"key":"2025011223511922900_qlae051-B11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12874-018-0502-1","article-title":"joinerml: A joint model and software package for time-to-event and multivariate longitudinal outcomes","volume":"18","author":"Hickey","year":"2018","journal-title":"BMC Medical Research Methodology"},{"key":"2025011223511922900_qlae051-B12","author":"Ioffe","year":"2015"},{"key":"2025011223511922900_qlae051-B13","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1109\/JBHI.6221020","article-title":"Dynamic prediction in clinical survival analysis using temporal convolutional networks","volume":"24","author":"Jarrett","year":"2019","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"key":"2025011223511922900_qlae051-B14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s41512-018-0045-2","article-title":"Dynamic models to predict health outcomes: Current status and methodological challenges","volume":"2","author":"Jenkins","year":"2018","journal-title":"Diagnostic and Prognostic Research"},{"issue":"1","key":"2025011223511922900_qlae051-B15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12874-017-0332-6","article-title":"Time-dependent ROC curve analysis in medical research: Current methods and applications","volume":"17","author":"Kamarudin","year":"2017","journal-title":"BMC Medical Research Methodology"},{"issue":"1","key":"2025011223511922900_qlae051-B16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12874-018-0482-1","article-title":"Deepsurv: Personalized treatment recommender system using a Cox proportional hazards deep neural network","volume":"18","author":"Katzman","year":"2018","journal-title":"BMC Medical Research Methodology"},{"key":"2025011223511922900_qlae051-B17","first-page":"1","article-title":"Time-to-event prediction with neural networks and Cox regression","volume":"20","author":"Kvamme","year":"2019","journal-title":"Journal of Machine Learning Research"},{"key":"2025011223511922900_qlae051-B18","author":"LeCun","year":"1998"},{"issue":"1","key":"2025011223511922900_qlae051-B19","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1109\/TBME.2019.2909027","article-title":"Dynamic-deephit: A deep learning approach for dynamic survival analysis with competing risks based on longitudinal data","volume":"67","author":"Lee","year":"2019","journal-title":"IEEE Transactions on Biomedical Engineering"},{"key":"2025011223511922900_qlae051-B20","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1609\/aaai.v32i1.11842","article-title":"Deephit: A deep learning approach to survival analysis with competing risks","volume":"32","author":"Lee","year":"2018","journal-title":"In Proceedings of the AAAI Conference on artificial intelligence"},{"issue":"2","key":"2025011223511922900_qlae051-B21","doi-asserted-by":"publisher","first-page":"435","DOI":"10.1111\/biom.v78.2","article-title":"Joint model for survival and multivariate sparse functional data with application to a study of Alzheimer\u2019s disease","volume":"78","author":"Li","year":"2022","journal-title":"Biometrics"},{"issue":"2","key":"2025011223511922900_qlae051-B22","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1177\/0962280217722177","article-title":"Dynamic predictions in Bayesian functional joint models for longitudinal and time-to-event data: An application to Alzheimer\u2019s disease","volume":"28","author":"Li","year":"2019","journal-title":"Statistical Methods in Medical Research"},{"key":"2025011223511922900_qlae051-B23","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1177\/0962280220941532","article-title":"Functional survival forests for multivariate longitudinal outcomes: Dynamic prediction of Alzheimer\u2019s disease progression","volume":"30","author":"Lin","year":"2021","journal-title":"Statistical Methods in Medical Research"},{"issue":"15","key":"2025011223511922900_qlae051-B24","doi-asserted-by":"publisher","first-page":"2894","DOI":"10.1002\/sim.9392","article-title":"Deep learning for the dynamic prediction of multivariate longitudinal and survival data","volume":"41","author":"Lin","year":"2022","journal-title":"Statistics in Medicine"},{"issue":"4","key":"2025011223511922900_qlae051-B25","doi-asserted-by":"publisher","first-page":"999","DOI":"10.1007\/s11222-020-09927-9","article-title":"Joint models with multiple longitudinal outcomes and a time-to-event outcome: A corrected two-stage approach","volume":"30","author":"Mauff","year":"2020","journal-title":"Statistics and Computing"},{"key":"2025011223511922900_qlae051-B26","author":"Nagpal","year":"2021"},{"key":"2025011223511922900_qlae051-B27","doi-asserted-by":"publisher","first-page":"1530","DOI":"10.1093\/aje\/kwy018","article-title":"Landmark models for optimizing the use of repeated measurements of risk factors in electronic health records to predict future disease risk","volume":"187","author":"Paige","year":"2018","journal-title":"American Journal of Epidemiology"},{"key":"2025011223511922900_qlae051-B28","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2025011223511922900_qlae051-B29","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1016\/j.ophtha.2018.11.015","article-title":"Deepseenet: A deep learning model for automated classification of patient-based age-related macular degeneration severity from color fundus photographs","volume":"126","author":"Peng","year":"2019","journal-title":"Ophthalmology"},{"key":"2025011223511922900_qlae051-B30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41746-020-00317-z","article-title":"Predicting risk of late age-related macular degeneration using deep learning","volume":"3","author":"Peng","year":"2020","journal-title":"NPJ Digital Medicine"},{"key":"2025011223511922900_qlae051-B31","author":"Putzel","year":"2021"},{"key":"2025011223511922900_qlae051-B32","doi-asserted-by":"publisher","first-page":"819","DOI":"10.1111\/biom.2011.67.issue-3","article-title":"Dynamic predictions and prospective accuracy in joint models for longitudinal and time-to-event data","volume":"67","author":"Rizopoulos","year":"2011","journal-title":"Biometrics"},{"key":"2025011223511922900_qlae051-B33","doi-asserted-by":"publisher","first-page":"1261","DOI":"10.1002\/bimj.v59.6","article-title":"Dynamic predictions with time-dependent covariates in survival analysis using joint modeling and landmarking","volume":"59","author":"Rizopoulos","year":"2017","journal-title":"Biometrical Journal"},{"key":"2025011223511922900_qlae051-B34","article-title":"Latent ordinary differential equations for irregularly sampled time series","volume":"32","author":"Rubanova","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"2025011223511922900_qlae051-B35","author":"Sloma","year":"2021"},{"key":"2025011223511922900_qlae051-B36","doi-asserted-by":"publisher","first-page":"2789","DOI":"10.1093\/bioinformatics\/btab039","article-title":"mlr3proba: An R package for machine learning in survival analysis","volume":"37","author":"Sonabend","year":"2021","journal-title":"Bioinformatics"},{"key":"2025011223511922900_qlae051-B37","doi-asserted-by":"publisher","first-page":"1929","DOI":"10.5555\/2627435.2670313","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"The Journal of Machine Learning Research"},{"key":"2025011223511922900_qlae051-B38","doi-asserted-by":"publisher","first-page":"750","DOI":"10.1002\/bimj.v53.5","article-title":"Joint modelling of longitudinal and time-to-event data with application to predicting abdominal aortic aneurysm growth and rupture","volume":"53","author":"Sweeting","year":"2011","journal-title":"Biometrical Journal"},{"key":"2025011223511922900_qlae051-B39","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1111\/rssa.12611","article-title":"Dynamic survival prediction combining landmarking with a machine learning ensemble: Methodology and empirical comparison","volume":"184","author":"Tanner","year":"2021","journal-title":"Journal of the Royal Statistical Society: Series A (Statistics in Society)"},{"key":"2025011223511922900_qlae051-B40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v061.c01","article-title":"Tutorial: Survival estimation for Cox regression models with time-varying coefficients using SAS and R","volume":"61","author":"Thomas","year":"2014","journal-title":"Journal of Statistical Software"},{"key":"2025011223511922900_qlae051-B41","first-page":"809","article-title":"Joint modeling of longitudinal and time-to-event data: An overview","volume":"14","author":"Tsiatis","year":"2004","journal-title":"Statistica Sinica"},{"key":"2025011223511922900_qlae051-B42","doi-asserted-by":"crossref","DOI":"10.1201\/b11311","volume-title":"Dynamic prediction in clinical survival analysis","author":"van Houwelingen","year":"2011"},{"key":"2025011223511922900_qlae051-B43","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1111\/sjos.2007.34.issue-1","article-title":"Dynamic prediction by landmarking in event history analysis","volume":"34","author":"Van Houwelingen","year":"2007","journal-title":"Scandinavian Journal of Statistics"},{"key":"2025011223511922900_qlae051-B44","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1038\/s42256-020-0154-9","article-title":"Deep-learning-based prediction of late age-related macular degeneration progression","volume":"2","author":"Yan","year":"2020","journal-title":"Nature Machine Intelligence"},{"issue":"3","key":"2025011223511922900_qlae051-B45","doi-asserted-by":"publisher","first-page":"1348","DOI":"10.1214\/21-AOS2153","article-title":"Deep learning for the partially linear Cox model","volume":"50","author":"Zhong","year":"2022","journal-title":"The Annals of Statistics"},{"issue":"10","key":"2025011223511922900_qlae051-B46","doi-asserted-by":"publisher","first-page":"1492","DOI":"10.1002\/sim.9683","article-title":"Multivariate functional mixed model with MRI data: An application to Alzheimer\u2019s disease","volume":"42","author":"Zou","year":"2023","journal-title":"Statistics in Medicine"}],"container-title":["Journal of the Royal Statistical Society Series C: Applied Statistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jrsssc\/article-pdf\/74\/1\/187\/59720586\/qlae051.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jrsssc\/article-pdf\/74\/1\/187\/59720586\/qlae051.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,12]],"date-time":"2025-01-12T23:51:36Z","timestamp":1736725896000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jrsssc\/article\/74\/1\/187\/7818263"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,11]]},"references-count":46,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,10,11]]},"published-print":{"date-parts":[[2025,1,13]]}},"URL":"https:\/\/doi.org\/10.1093\/jrsssc\/qlae051","relation":{},"ISSN":["0035-9254","1467-9876"],"issn-type":[{"value":"0035-9254","type":"print"},{"value":"1467-9876","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,1]]},"published":{"date-parts":[[2024,10,11]]}}}