{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T15:45:46Z","timestamp":1792079146415,"version":"4.4.0"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T00:00:00Z","timestamp":1792022400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T00:00:00Z","timestamp":1792022400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"NIH","award":["R01CA249096-05"],"award-info":[{"award-number":["R01CA249096-05"]}]},{"name":"NIH","award":["R01CA269398"],"award-info":[{"award-number":["R01CA269398"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Lifetime Data Anal"],"published-print":{"date-parts":[[2026,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Estimating heterogeneous treatment effects in survival settings is complicated by right censoring as well as the time-varying nature of the estimand. While the conditional average treatment effect (CATE) provides a natural target, most existing approaches focus on a single prespecified time point and do not account for temporal trajectory, leading to instability in estimation. We propose a deep survival learner (DSL) for estimating heterogeneous treatment effects with right-censored outcomes. The method is based on a doubly robust pseudo-outcome whose conditional expectation identifies time-specific CATEs under standard assumptions. This construction remains unbiased if either the outcome model or the treatment assignment model is correctly specified, when properly accounting for censoring. To estimate CATEs over a clinically relevant time spectrum, DSL employs a multi-output deep neural network with shared representations, enabling joint estimation of treatment effect trajectories. From a theoretical perspective, we derive error bounds for both pointwise and joint estimation over time. We show that joint estimation can leverage temporal structure to control estimation error without incurring much additional approximation cost under smoothness conditions, leading to improved stability relative to separate estimation. Cross-fitting is incorporated to reduce overfitting and mitigate bias arising from flexible nuisance estimation. Simulation studies demonstrate favorable finite-sample performance, particularly under nuisance model misspecification. Applied to the Boston Lung Cancer Study, DSL reveals heterogeneity in the effects of perioperative chemotherapy across patient characteristics and over time.<\/jats:p>","DOI":"10.1007\/s10985-026-09734-w","type":"journal-article","created":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T15:04:28Z","timestamp":1792076668000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Estimating heterogeneous treatment effects with survival outcomes via a deep survival learner"],"prefix":"10.1007","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5705-5553","authenticated-orcid":false,"given":"Yuming","family":"Sun","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,10,15]]},"reference":[{"issue":"2","key":"9734_CR1","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1016\/j.cllc.2025.09.007","volume":"27","author":"AAR Alvarez","year":"2026","unstructured":"Alvarez AAR, Sun Y, Li Y, Christiani DC (2026) Effects of sex on mortality in patients with lung cancer: a multiple mediation analysis of the Boston Lung Cancer Study. Clin Lung Cancer 27(2):201-209.e3","journal-title":"Clin Lung Cancer"},{"issue":"4","key":"9734_CR2","doi-asserted-by":"publisher","first-page":"1100","DOI":"10.1214\/aos\/1176345976","volume":"10","author":"PK Andersen","year":"1982","unstructured":"Andersen PK, Gill RD (1982) Cox\u2019s regression model for counting processes: a large sample study. Ann Stat 10(4):1100\u20131120","journal-title":"Ann Stat"},{"issue":"1","key":"9734_CR3","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1200\/JCO.2009.23.2272","volume":"28","author":"R Arriagada","year":"2010","unstructured":"Arriagada R, Dunant A, Pignon J-P, Bergman B, Chabowski M, Grunenwald D, Kozlowski M, Le P\u00e9choux C, Pirker R, Pinel M-I et al (2010) Long-term results of the international adjuvant lung cancer trial evaluating adjuvant cisplatin-based chemotherapy in resected lung cancer. J Clin Oncol 28(1):35\u201342","journal-title":"J Clin Oncol"},{"key":"9734_CR4","unstructured":"Bartlett PL, Foster DJ, Telgarsky M (2017) Spectrally-normalized margin bounds for neural networks. Adv Neural Informat Proc Syst. p 30"},{"issue":"3\u20134","key":"9734_CR5","doi-asserted-by":"publisher","DOI":"10.1002\/sim.10333","volume":"44","author":"N Bo","year":"2025","unstructured":"Bo N, Jeong J-H, Forno E, Ding Y (2025) Evaluating meta-learners to analyze treatment heterogeneity in survival data: application to electronic health records of pediatric asthma care in covid-19 pandemic. Stat Med 44(3\u20134):e10333","journal-title":"Stat Med"},{"issue":"1","key":"9734_CR6","doi-asserted-by":"publisher","first-page":"C1","DOI":"10.1111\/ectj.12097","volume":"21","author":"V Chernozhukov","year":"2018","unstructured":"Chernozhukov V, Chetverikov D, Demirer M, Duflo E, Hansen C, Newey W, Robins J (2018) Double\/debiased machine learning for treatment and structural parameters. Economet J 21(1):C1\u2013C68","journal-title":"Economet J"},{"issue":"2","key":"9734_CR7","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1093\/jrsssb\/qkac001","volume":"85","author":"Y Cui","year":"2023","unstructured":"Cui Y, Kosorok MR, Sverdrup E, Wager S, Zhu R (2023) Estimating heterogeneous treatment effects with right-censored data via causal survival forests. J R Stat Soc Ser B Stat Methodol 85(2):179\u2013211","journal-title":"J R Stat Soc Ser B Stat Methodol"},{"key":"9734_CR8","first-page":"26740","volume":"34","author":"A Curth","year":"2021","unstructured":"Curth A, Lee C, van der Schaar M (2021) Survite: learning heterogeneous treatment effects from time-to-event data. Adv Neural Inf Process Syst 34:26740\u201326753","journal-title":"Adv Neural Inf Process Syst"},{"issue":"3","key":"9734_CR9","doi-asserted-by":"publisher","first-page":"392","DOI":"10.1177\/09622802231224628","volume":"33","author":"S Dandl","year":"2024","unstructured":"Dandl S, Bender A, Hothorn T (2024) Heterogeneous treatment effect estimation for observational data using model-based forests. Stat Methods Med Res 33(3):392\u2013413","journal-title":"Stat Methods Med Res"},{"key":"9734_CR10","volume-title":"A practical guide to splines","author":"C de Boor","year":"2001","unstructured":"de Boor C (2001) A practical guide to splines. Springer, Verlag"},{"issue":"3","key":"9734_CR11","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1016\/j.amepre.2017.03.023","volume":"53","author":"SH Dharmarajan","year":"2017","unstructured":"Dharmarajan SH, Bragg-Gresham JL, Morgenstern H, Gillespie BW, Li Y, Powe NR, Tuot DS, Banerjee T, R\u0131os Burrows N, Rolka DB, Saydah SH, Saran R (2017) State-level awareness of chronic kidney disease in the US. Am J Prev Med 53(3):300\u2013307. https:\/\/doi.org\/10.1016\/j.amepre.2017.03.023","journal-title":"Am J Prev Med"},{"issue":"9","key":"9734_CR12","doi-asserted-by":"publisher","first-page":"719","DOI":"10.1016\/S1470-2045(06)70804-X","volume":"7","author":"J-Y Douillard","year":"2006","unstructured":"Douillard J-Y, Rosell R, De Lena M, Carpagnano F, Ramlau R, Gonz\u00e1les-Larriba JL, Grodzki T, Pereira JR, Le Groumellec A, Lorusso V et al (2006) Adjuvant vinorelbine plus cisplatin versus observation in patients with completely resected stage IB-IIIA non-small-cell lung cancer (adjuvant navelbine international trialist association [ANITA]): a randomised controlled trial. Lancet Oncol 7(9):719\u2013727","journal-title":"Lancet Oncol"},{"key":"9734_CR13","volume-title":"A distribution-free theory of nonparametric regression","author":"L Gy\u00f6rfi","year":"2006","unstructured":"Gy\u00f6rfi L, Kohler M, Krzy\u017cak A, Walk H (2006) A distribution-free theory of nonparametric regression. Springer"},{"issue":"8","key":"9734_CR14","doi-asserted-by":"publisher","first-page":"812","DOI":"10.1016\/j.oraloncology.2007.09.004","volume":"44","author":"R Haddad","year":"2008","unstructured":"Haddad R, Crum C, Chen Z, Krane J, Posner M, Li Y, Burk R (2008) HPV16 transmission between a couple with HPV-related head and neck cancer. Oral Oncol 44(8):812\u2013815. https:\/\/doi.org\/10.1016\/j.oraloncology.2007.09.004","journal-title":"Oral Oncol"},{"issue":"260","key":"9734_CR15","doi-asserted-by":"publisher","first-page":"663","DOI":"10.1080\/01621459.1952.10483446","volume":"47","author":"DG Horvitz","year":"1952","unstructured":"Horvitz DG, Thompson DJ (1952) A generalization of sampling without replacement from a finite universe. J Am Stat Assoc 47(260):663\u2013685","journal-title":"J Am Stat Assoc"},{"issue":"1","key":"9734_CR16","doi-asserted-by":"publisher","DOI":"10.1002\/bimj.202200178","volume":"66","author":"L Hu","year":"2024","unstructured":"Hu L (2024) A new method for clustered survival data: estimation of treatment effect heterogeneity and variable selection. Biom J 66(1):2200178","journal-title":"Biom J"},{"key":"9734_CR17","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139025751","volume-title":"Causal inference for statistics, social, and biomedical sciences: an introduction","author":"GW Imbens","year":"2015","unstructured":"Imbens GW, Rubin DB (2015) Causal inference for statistics, social, and biomedical sciences: an introduction. Cambridge University Press"},{"key":"9734_CR18","volume-title":"Causal inference for statistics social and biomedical sciences: An introduction","author":"GW Imbens","year":"2016","unstructured":"Imbens GW, Rubin DB (2016) Causal inference for statistics social and biomedical sciences: An introduction. Taylor Francis"},{"key":"9734_CR19","unstructured":"Kennedy EH (2020) Towards optimal doubly robust estimation of heterogeneous causal effects. arXiv preprint arXiv:2004.14497"},{"issue":"10","key":"9734_CR20","doi-asserted-by":"publisher","first-page":"4156","DOI":"10.1073\/pnas.1804597116","volume":"116","author":"SR K\u00fcnzel","year":"2019","unstructured":"K\u00fcnzel SR, Sekhon JS, Bickel PJ, Yu B (2019) Metalearners for estimating heterogeneous treatment effects using machine learning. Proc Natl Acad Sci 116(10):4156\u20134165","journal-title":"Proc Natl Acad Sci"},{"issue":"11","key":"9734_CR21","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0263911","volume":"17","author":"A Leiter","year":"2022","unstructured":"Leiter A, Kong CY, Gould MK, Kale MS, Veluswamy RR, Smith CB, Mhango G, Huang BZ, Wisnivesky JP, Sigel K (2022) The benefits and harms of adjuvant chemotherapy for non-small cell lung cancer in patients with major comorbidities: a simulation study. PLoS One 17(11):e0263911","journal-title":"PLoS One"},{"issue":"2","key":"9734_CR22","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1093\/biomet\/asaa076","volume":"108","author":"X Nie","year":"2021","unstructured":"Nie X, Wager S (2021) Quasi-oracle estimation of heterogeneous treatment effects. Biometrika 108(2):299\u2013319","journal-title":"Biometrika"},{"issue":"1","key":"9734_CR23","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1093\/biomet\/70.1.41","volume":"70","author":"PR Rosenbaum","year":"1983","unstructured":"Rosenbaum PR, Rubin DB (1983) The central role of the propensity score in observational studies for causal effects. Biometrika 70(1):41\u201355","journal-title":"Biometrika"},{"issue":"8","key":"9734_CR24","doi-asserted-by":"publisher","first-page":"1411","DOI":"10.1080\/01635581.2020.1801774","volume":"73","author":"A Sakin","year":"2021","unstructured":"Sakin A, Sahin S, Mustafa Atci M, Yasar N, Demir C, Geredeli C, Sakin A, Cihan S (2021) The effect of body mass index on treatment outcomes in patients with metastatic non-small cell lung cancer treated with platinum-based therapy. Nutr Cancer 73(8):1411\u20131418","journal-title":"Nutr Cancer"},{"key":"9734_CR25","doi-asserted-by":"publisher","first-page":"638","DOI":"10.1245\/s10434-015-4902-8","volume":"23","author":"BJ Sandler","year":"2016","unstructured":"Sandler BJ, Wang Z, Hancock JG, Boffa DJ, Detterbeck FC, Kim AW (2016) Gender, age, and comorbidity status predict improved survival with adjuvant chemotherapy following lobectomy for non-small cell lung cancers larger than 4 cm. Ann Surg Oncol 23:638\u2013645","journal-title":"Ann Surg Oncol"},{"issue":"52","key":"9734_CR26","first-page":"1","volume":"21","author":"J Schmidt-Hieber","year":"2020","unstructured":"Schmidt-Hieber J (2020) Deep relu network approximation of functions on a manifold. J Mach Learn Res 21(52):1\u201326","journal-title":"J Mach Learn Res"},{"key":"9734_CR27","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511618994","volume-title":"Spline functions: Basic theory","author":"LL Schumaker","year":"2007","unstructured":"Schumaker LL (2007) Spline functions: Basic theory, 3rd edn. Cambridge University Press. https:\/\/doi.org\/10.1017\/CBO9780511618994","edition":"3rd"},{"issue":"508","key":"9734_CR28","doi-asserted-by":"publisher","first-page":"1517","DOI":"10.1080\/01621459.2014.951443","volume":"109","author":"L Tian","year":"2014","unstructured":"Tian L, Alizadeh AA, Gentles AJ, Tibshirani R (2014) A simple method for estimating interactions between a treatment and a large number of covariates. J Am Stat Assoc 109(508):1517\u20131532","journal-title":"J Am Stat Assoc"},{"key":"9734_CR29","volume-title":"Semiparametric theory and missing data","author":"AA Tsiatis","year":"2006","unstructured":"Tsiatis AA (2006) Semiparametric theory and missing data. Springer"},{"key":"9734_CR30","doi-asserted-by":"publisher","DOI":"10.1007\/b13794","volume-title":"Introduction to nonparametric estimation","author":"AB Tsybakov","year":"2009","unstructured":"Tsybakov AB (2009) Introduction to nonparametric estimation. Springer. https:\/\/doi.org\/10.1007\/b13794"},{"key":"9734_CR31","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511802256","volume-title":"Asymptotic statistics","author":"AW van der Vaart","year":"1998","unstructured":"van der Vaart AW (1998) Asymptotic statistics. Cambridge University Press"},{"key":"9734_CR32","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4757-2545-2","volume-title":"Weak convergence and empirical processes","author":"AW van der Vaart","year":"1996","unstructured":"van der Vaart AW, Wellner JA (1996) Weak convergence and empirical processes. Springer"},{"issue":"5","key":"9734_CR33","doi-asserted-by":"publisher","first-page":"e2311966","DOI":"10.1001\/jamanetworkopen.2023.11966","volume":"6","author":"X Wang","year":"2023","unstructured":"Wang X, Romero-Gutierrez CW, Kothari J, Shafer A, Li Y, Christiani DC (2023) Prediagnosis smoking cessation and overall survival among patients with non-small cell lung cancer. JAMA Netw Open 6(5):e2311966","journal-title":"JAMA Netw Open"},{"key":"9734_CR34","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1201\/9781003102670-21","volume-title":"Handbook of matching and weighting adjustments for causal inference","author":"Y Xu","year":"2023","unstructured":"Xu Y, Ignatiadis N, Sverdrup E, Fleming S, Wager S, Shah N (2023) Treatment heterogeneity with survival outcomes. Handbook of matching and weighting adjustments for causal inference. Chapman; Hall\/CRC, pp 445\u2013482"},{"issue":"23\u201324","key":"9734_CR35","doi-asserted-by":"publisher","DOI":"10.1002\/sim.70301","volume":"44","author":"Y Yang","year":"2025","unstructured":"Yang Y, Hu W, Liao Z, Chen F (2025) Doubly robust estimators for heterogeneous treatment effects in heteroskedastic survival data. Stat Med 44(23\u201324):e70301","journal-title":"Stat Med"},{"issue":"24","key":"9734_CR36","doi-asserted-by":"publisher","first-page":"4796","DOI":"10.1002\/cam4.4808","volume":"11","author":"T Zhai","year":"2022","unstructured":"Zhai T, Li Y, Brown R, Lanuti M, Gainor JF, Christiani DC (2022) Spirometry at diagnosis and overall survival in non-small cell lung cancer patients. Cancer Med 11(24):4796\u20134805","journal-title":"Cancer Med"},{"issue":"3","key":"9734_CR37","doi-asserted-by":"publisher","first-page":"434","DOI":"10.1016\/j.lungcan.2007.10.013","volume":"60","author":"Z Zhang","year":"2008","unstructured":"Zhang Z, Xu F, Wang S, Li N, Wang C (2008) Influence of smoking on histologic type and the efficacy of adjuvant chemotherapy in resected non-small cell lung cancer. Lung Cancer 60(3):434\u2013440","journal-title":"Lung Cancer"}],"container-title":["Lifetime Data Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10985-026-09734-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10985-026-09734-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10985-026-09734-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T15:04:32Z","timestamp":1792076672000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10985-026-09734-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,15]]},"references-count":37,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,12]]}},"alternative-id":["9734"],"URL":"https:\/\/doi.org\/10.1007\/s10985-026-09734-w","relation":{},"ISSN":["1380-7870","1572-9249"],"issn-type":[{"value":"1380-7870","type":"print"},{"value":"1572-9249","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,15]]},"assertion":[{"value":"27 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 September 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 October 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"54"}}