{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T01:35:43Z","timestamp":1780450543548,"version":"3.54.1"},"reference-count":31,"publisher":"Oxford University Press (OUP)","issue":"2","license":[{"start":{"date-parts":[[2017,9,28]],"date-time":"2017-09-28T00:00:00Z","timestamp":1506556800000},"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\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["NS073671"],"award-info":[{"award-number":["NS073671"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["NS082062"],"award-info":[{"award-number":["NS082062"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,6,1]]},"abstract":"<jats:title>Summary<\/jats:title>\n               <jats:p>In clinical practice, an informative and practically useful treatment rule should be simple and transparent. However, because simple rules are likely to be far from optimal, effective methods to construct such rules must guarantee performance, in terms of yielding the best clinical outcome (highest reward) among the class of simple rules under consideration. Furthermore, it is important to evaluate the benefit of the derived rules on the whole sample and in pre-specified subgroups (e.g., vulnerable patients). To achieve both goals, we propose a robust machine learning method to estimate a linear treatment rule that is guaranteed to achieve optimal reward among the class of all linear rules. We then develop a diagnostic measure and inference procedure to evaluate the benefit of the obtained rule and compare it with the rules estimated by other methods. We provide theoretical justification for the proposed method and its inference procedure, and we demonstrate via simulations its superior performance when compared to existing methods. Lastly, we apply the method to the Sequenced Treatment Alternatives to Relieve Depression (STAR*D) trial on major depressive disorder and show that the estimated optimal linear rule provides a large benefit for mildly depressed and severely depressed patients but manifests a lack-of-fit for moderately depressed patients.<\/jats:p>","DOI":"10.1111\/biom.12773","type":"journal-article","created":{"date-parts":[[2017,9,28]],"date-time":"2017-09-28T17:06:35Z","timestamp":1506618395000},"page":"517-528","source":"Crossref","is-referenced-by-count":14,"title":["Estimation and Evaluation of Linear Individualized Treatment Rules to Guarantee Performance"],"prefix":"10.1093","volume":"74","author":[{"given":"Xin","family":"Qiu","sequence":"first","affiliation":[{"name":"Department of Biostatistics, Columbia University , New York, NY , U.S.A."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0843-9280","authenticated-orcid":false,"given":"Donglin","family":"Zeng","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, University of North Carolina at Chapel Hill , Chapel Hill, North Carolina , U.S.A."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1510-3315","authenticated-orcid":false,"given":"Yuanjia","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, Columbia University , New York, NY , U.S.A."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2017,9,28]]},"reference":[{"key":"2024011406322031400_biom12773-bib-0001","doi-asserted-by":"crossref","first-page":"117","DOI":"10.1016\/0167-6377(96)00022-3","article-title":"Numerical solution for optimization over the efficient set by D.C. optimization algorithms","volume":"19","author":"An","year":"1996","journal-title":"Operations Research Letters"},{"key":"2024011406322031400_biom12773-bib-0002","doi-asserted-by":"crossref","first-page":"7353","DOI":"10.1073\/pnas.1510489113","article-title":"Recursive partitioning for heterogeneous causal effects","volume":"113","author":"Athey","year":"2016","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"2024011406322031400_biom12773-bib-0003","author":"Blatt","year":"2004","journal-title":"A-Learning for Approximate Planning"},{"key":"2024011406322031400_biom12773-bib-0004","doi-asserted-by":"crossref","DOI":"10.1136\/bmj.f540","article-title":"Influence of initial severity of depression on effectiveness of low intensity interventions: meta-analysis of individual patient data","volume":"346","author":"Bower","year":"2013","journal-title":"BMJ"},{"key":"2024011406322031400_biom12773-bib-0005","doi-asserted-by":"crossref","DOI":"10.1201\/b16749","volume-title":"Clinical and Statistical Considerations in Personalized Medicine","author":"Carini","year":"2014"},{"key":"2024011406322031400_biom12773-bib-0006","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4614-7428-9","volume-title":"Statistical methods for dynamic treatment regimes","author":"Chakraborty","year":"2013"},{"key":"2024011406322031400_biom12773-bib-0007","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1145\/1143844.1143870","article-title":"Trading convexity for scalability","volume-title":"Proceedings of the 23rd International Conference on Machine Learning","author":"Collobert","year":"2006"},{"key":"2024011406322031400_biom12773-bib-0008","doi-asserted-by":"crossref","first-page":"2221","DOI":"10.1002\/sim.6859","article-title":"Q-learning residual analysis: Application to the effectiveness of sequences of antipsychotic medications for patients with schizophrenia","volume":"35","author":"Ertefaie","year":"2016","journal-title":"Statistics in Medicine"},{"key":"2024011406322031400_biom12773-bib-0009","article-title":"Concordance-assisted learning for estimating optimal individualized treatment regimes","author":"Fan","year":"2016","journal-title":"Journal of the Royal Statistical Society: Series B (Statistical Methodology)"},{"key":"2024011406322031400_biom12773-bib-0010","doi-asserted-by":"crossref","first-page":"2867","DOI":"10.1002\/sim.4322","article-title":"Subgroup identification from randomized clinical trial data","volume":"30","author":"Foster","year":"2011","journal-title":"Statistics in Medicine"},{"key":"2024011406322031400_biom12773-bib-0011","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1016\/j.stamet.2009.05.003","article-title":"Variable selection for qualitative interactions","volume":"8","author":"Gunter","year":"2011","journal-title":"Statistical Methodology"},{"key":"2024011406322031400_biom12773-bib-0012","doi-asserted-by":"crossref","first-page":"891","DOI":"10.1111\/biom.12204","article-title":"Identifying optimal biomarker combinations for treatment selection via a robust kernel method","volume":"70","author":"Huang","year":"2014","journal-title":"Biometrics"},{"key":"2024011406322031400_biom12773-bib-0013","doi-asserted-by":"crossref","first-page":"91","DOI":"10.4088\/PCC.v10n0201","article-title":"What are the implications of the STAR* D trial for primary care? A review and synthesis","volume":"10","author":"Huynh","year":"2008","journal-title":"Primary Care Companion to the Journal of Clinical Psychiatry"},{"key":"2024011406322031400_biom12773-bib-0014","doi-asserted-by":"crossref","first-page":"831","DOI":"10.1093\/biomet\/asu043","article-title":"Interactive model building for q-learning","volume":"101","author":"Laber","year":"2014","journal-title":"Biometrika"},{"key":"2024011406322031400_biom12773-bib-0015","doi-asserted-by":"crossref","first-page":"904","DOI":"10.1198\/jasa.2010.tm10053","article-title":"Adaptive confidence intervals for the test error in classification","volume":"106","author":"Laber","year":"2011","journal-title":"Journal of the American Statistical Association"},{"key":"2024011406322031400_biom12773-bib-0016","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1191\/1740774S04cn002oa","article-title":"Dynamic treatment regimes: practical design considerations","volume":"1","author":"Lavori","year":"2004","journal-title":"Clinical Trials"},{"key":"2024011406322031400_biom12773-bib-0017","author":"Liu","year":"2014","journal-title":"Robust hybrid learning for estimating personalized dynamic treatment regimens"},{"key":"2024011406322031400_biom12773-bib-0018","article-title":"Generalization bounds and consistency for latent structural probit and ramp loss","author":"McAllester","year":"2011","journal-title":"Neural Information Processing Systems"},{"key":"2024011406322031400_biom12773-bib-0019","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1111\/1467-9868.00389","article-title":"Optimal dynamic treatment regimes","volume":"65","author":"Murphy","year":"2003","journal-title":"Journal of the Royal Statistical Society: Series B (Statistical Methodology)"},{"key":"2024011406322031400_biom12773-bib-0020","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1137\/S0097539792240406","article-title":"Sparse approximate solutions to linear systems","volume":"24","author":"Natarajan","year":"1995","journal-title":"SIAM Journal on Computing"},{"key":"2024011406322031400_biom12773-bib-0021","doi-asserted-by":"crossref","first-page":"1180","DOI":"10.1214\/10-AOS864","article-title":"Performance guarantees for individualized treatment rules","volume":"39","author":"Qian","year":"2011","journal-title":"Annals of Statistics"},{"key":"2024011406322031400_biom12773-bib-0022","doi-asserted-by":"crossref","DOI":"10.2202\/1557-4679.1210","article-title":"Model checking with residuals for g-estimation of optimal dynamic treatment regimes","volume":"6","author":"Rich","year":"2010","journal-title":"The International Journal of Biostatistics"},{"key":"2024011406322031400_biom12773-bib-0023","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/S0197-2456(03)00112-0","article-title":"Sequenced treatment alternatives to relieve depression (STAR*D): Rationale and design","volume":"25","author":"Rush","year":"2004","journal-title":"Controlled Clinical Trials"},{"key":"2024011406322031400_biom12773-bib-0024","doi-asserted-by":"crossref","first-page":"640","DOI":"10.1214\/13-STS450","article-title":"Q-and a-learning methods for estimating optimal dynamic treatment regimes","volume":"29","author":"Schulte","year":"2014","journal-title":"Statistical Science: A Review Journal of the Institute of Mathematical Statistics"},{"key":"2024011406322031400_biom12773-bib-0025","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1176\/appi.ajp.163.1.28","article-title":"Evaluation of outcomes with citalopram for depression using measurement-based care in STAR*D: Implications for clinical practice","volume":"163","author":"Trivedi","year":"2006","journal-title":"American Journal of Psychiatry"},{"key":"2024011406322031400_biom12773-bib-0026","doi-asserted-by":"crossref","first-page":"855","DOI":"10.1111\/biom.12468","article-title":"Model assessment in dynamic treatment regimen estimation via double robustness","volume":"72","author":"Wallace","year":"2016","journal-title":"Biometrics"},{"key":"2024011406322031400_biom12773-bib-0027","volume-title":"Learning from delayed rewards","author":"Watkins","year":"1989"},{"key":"2024011406322031400_biom12773-bib-0028","doi-asserted-by":"crossref","first-page":"1010","DOI":"10.1111\/j.1541-0420.2012.01763.x","article-title":"A robust method for estimating optimal treatment regimes","volume":"68","author":"Zhang","year":"2012","journal-title":"Biometrics"},{"key":"2024011406322031400_biom12773-bib-0029","doi-asserted-by":"crossref","first-page":"681","DOI":"10.1093\/biomet\/ast014","article-title":"Robust estimation of optimal dynamic treatment regimes for sequential treatment decisions","volume":"100","author":"Zhang","year":"2013","journal-title":"Biometrika"},{"key":"2024011406322031400_biom12773-bib-0030","doi-asserted-by":"crossref","first-page":"1106","DOI":"10.1080\/01621459.2012.695674","article-title":"Estimating individualized treatment rules using outcome weighted learning","volume":"107","author":"Zhao","year":"2012","journal-title":"Journal of the American Statistical Association"},{"key":"2024011406322031400_biom12773-bib-0031","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1080\/01621459.2014.937488","article-title":"New statistical learning methods for estimating optimal dynamic treatment regimes","volume":"110","author":"Zhao","year":"2015","journal-title":"Journal of the American Statistical Association"}],"container-title":["Biometrics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1111%2Fbiom.12773","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/academic.oup.com\/biometrics\/article-pdf\/74\/2\/517\/55617657\/biometrics_74_2_517.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/biometrics\/article-pdf\/74\/2\/517\/55617657\/biometrics_74_2_517.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,26]],"date-time":"2024-01-26T18:05:47Z","timestamp":1706292347000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/biometrics\/article\/74\/2\/517-528\/7521348"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,9,28]]},"references-count":31,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2017,9,28]]},"published-print":{"date-parts":[[2018,6,1]]}},"URL":"https:\/\/doi.org\/10.1111\/biom.12773","relation":{},"ISSN":["0006-341X","1541-0420"],"issn-type":[{"value":"0006-341X","type":"print"},{"value":"1541-0420","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2018,6]]},"published":{"date-parts":[[2017,9,28]]}}}