{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T10:32:01Z","timestamp":1783161121305,"version":"3.54.6"},"reference-count":40,"publisher":"Wiley","issue":"4","license":[{"start":{"date-parts":[[2023,2,3]],"date-time":"2023-02-03T00:00:00Z","timestamp":1675382400000},"content-version":"am","delay-in-days":365,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#am"},{"start":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T00:00:00Z","timestamp":1643846400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1416953"],"award-info":[{"award-number":["1416953"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1636840"],"award-info":[{"award-number":["1636840"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1734853"],"award-info":[{"award-number":["1734853"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1916425"],"award-info":[{"award-number":["1916425"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01CA233487"],"award-info":[{"award-number":["R01CA233487"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01MH121079"],"award-info":[{"award-number":["R01MH121079"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01MH126137"],"award-info":[{"award-number":["R01MH126137"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["T32GM141746"],"award-info":[{"award-number":["T32GM141746"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["UL1TR002240"],"award-info":[{"award-number":["UL1TR002240"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Biometrical J"],"published-print":{"date-parts":[[2022,4]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The wide\u2010scale adoption of electronic health records (EHRs) provides extensive information to support precision medicine and personalized health care. In addition to structured EHRs, we leverage free\u2010text clinical information extraction (IE) techniques to estimate optimal dynamic treatment regimes (DTRs), a sequence of decision rules that dictate how to individualize treatments to patients based on treatment and covariate history. The proposed IE of patient characteristics closely resembles \u201cThe clinical Text Analysis and Knowledge Extraction System\u201d and employs named entity recognition, boundary detection, and negation annotation. It also utilizes regular expressions to extract numerical information. Combining the proposed IE with optimal DTR estimation, we extract derived patient characteristics and use tree\u2010based reinforcement learning (T\u2010RL) to estimate multistage optimal DTRs. IE significantly improved the estimation in counterfactual outcome models compared to using structured EHR data alone, which often include incomplete data, data entry errors, and other potentially unobserved risk factors. Moreover, including IE in optimal DTR estimation provides larger study cohorts and a broader pool of candidate tailoring variables. We demonstrate the performance of our proposed method via simulations and an application using clinical records to guide blood pressure control treatments among critically ill patients with severe acute hypertension. This joint estimation approach improves the accuracy of identifying the optimal treatment sequence by 14\u201324% compared to traditional inference without using IE, based on our simulations over various scenarios. In the blood pressure control application, we successfully extracted significant blood pressure predictors that are unobserved or partially missing from structured\u00a0EHR.<\/jats:p>","DOI":"10.1002\/bimj.202100077","type":"journal-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T10:55:48Z","timestamp":1643885748000},"page":"805-817","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Optimal dynamic treatment regime estimation using information extraction from unstructured clinical text"],"prefix":"10.1002","volume":"64","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1649-3458","authenticated-orcid":false,"given":"Nina","family":"Zhou","sequence":"first","affiliation":[{"name":"Department of Biostatistics University of Michigan  Ann Arbor MI USA"},{"name":"Statistics Online Computational Resource University of Michigan  Ann Arbor MI USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert D.","family":"Brook","sequence":"additional","affiliation":[{"name":"Division of Cardiovascular Diseases School of Medicine Wayne State University  Detroit MI USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ivo D.","family":"Dinov","sequence":"additional","affiliation":[{"name":"Statistics Online Computational Resource University of Michigan  Ann Arbor MI USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4066-5026","authenticated-orcid":false,"given":"Lu","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Biostatistics University of Michigan  Ann Arbor MI USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2022,2,3]]},"reference":[{"issue":"6","key":"e_1_2_9_2_1","first-page":"545","article-title":"Health effects of tobacco use and exposure","volume":"56","author":"Bartal M.","year":"2001","journal-title":"Monaldi Archives for Chest Disease"},{"key":"e_1_2_9_3_1","first-page":"2491","article-title":"Measurement error in epidemiologic studies","volume":"3","author":"Carroll R. J.","year":"1998","journal-title":"Encyclopedia of Biostatistics"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1993.10594310"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1201\/9781420010138"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-statistics-022513-115553"},{"key":"e_1_2_9_7_1","doi-asserted-by":"publisher","DOI":"10.5888\/pcd15.180371"},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1191\/096228098668199908"},{"key":"e_1_2_9_9_1","doi-asserted-by":"publisher","DOI":"10.1002\/sim.4322"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1198\/016214501753168154"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2016.35"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1017\/S1351324997001563"},{"issue":"1","key":"e_1_2_9_13_1","article-title":"Targeted maximum likelihood learning","volume":"2","author":"Laan M. J. V. D.","year":"2006","journal-title":"International Journal of Biostatistics"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/asv028"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1993.10594302"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1080\/10618600.2017.1356325"},{"key":"e_1_2_9_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.amjhyper.2007.03.011"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1378\/chest.06-2490"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocy170"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1198\/016214501753382327"},{"key":"e_1_2_9_21_1","volume-title":"The prevention and treatment of missing data in clinical trials","author":"National Research Council and others","year":"2010"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.1002\/sim.6753"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/0270-0255(86)90088-6"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1080\/03610929408831393"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-1842-5_4"},{"key":"e_1_2_9_26_1","doi-asserted-by":"crossref","unstructured":"Robins J. M.(2004).Optimal structural nested models for optimal sequential decisions. InProceedings of the Second Seattle Symposium in Biostatistics(pp.189\u2013326).","DOI":"10.1007\/978-1-4419-9076-1_11"},{"key":"e_1_2_9_27_1","volume-title":"Multiple imputation for nonresponse in surveys","author":"Rubin D. B.","year":"2004"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1186\/2110-5820-3-17"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1136\/jamia.2009.001560"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1161\/hc4101.096153"},{"issue":"4","key":"e_1_2_9_31_1","first-page":"S2","article-title":"Hypertensive urgencies and emergencies","volume":"14","author":"Shafi T.","year":"2004","journal-title":"Ethnicity & Disease"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btr597"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1751-7133.2008.00047.x"},{"issue":"2","key":"e_1_2_9_34_1","first-page":"141","article-title":"Subgroup analysis via recursive partitioning","volume":"10","author":"Su X.","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_9_35_1","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.109.896597"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1111\/biom.12539"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1214\/18-AOAS1137"},{"key":"e_1_2_9_38_1","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2011.641416"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.1161\/01.HYP.0000200710.29498.80"},{"key":"e_1_2_9_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2017.11.011"},{"key":"e_1_2_9_41_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.328.7440.634"}],"container-title":["Biometrical Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/bimj.202100077","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/bimj.202100077","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/am-pdf\/10.1002\/bimj.202100077","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/bimj.202100077","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,25]],"date-time":"2023-08-25T20:52:39Z","timestamp":1692996759000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/bimj.202100077"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,3]]},"references-count":40,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,4]]}},"alternative-id":["10.1002\/bimj.202100077"],"URL":"https:\/\/doi.org\/10.1002\/bimj.202100077","archive":["Portico"],"relation":{},"ISSN":["0323-3847","1521-4036"],"issn-type":[{"value":"0323-3847","type":"print"},{"value":"1521-4036","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,2,3]]},"assertion":[{"value":"2021-03-07","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-10-21","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-02-03","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}