{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,15]],"date-time":"2026-10-15T16:33:30Z","timestamp":1792082010901,"version":"4.4.0"},"reference-count":31,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T00:00:00Z","timestamp":1744070400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["ascpt.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Clin Pharma and Therapeutics"],"published-print":{"date-parts":[[2025,7]]},"abstract":"<jats:p>Measuring medication discontinuation in claims data primarily relies on the gaps between prescription fills, but such definitions are rarely validated. This study aimed to establish a natural language processing (NLP)\u2010based validation framework to evaluate the performance of claims\u2010based discontinuation algorithms for commonly used medications against NLP\u2010based reference standards from electronic health records (EHRs). A total of 36,656 patients receiving antipsychotic medications (APMs), benzodiazepines (BZDs), warfarin, or direct oral anticoagulants (DOACs) were identified from the Mass General Brigham EHRs in 2007\u20132020. These EHR data were linked with 97,900 Medicare Part D claims. An NLP\u2010aided chart review was applied to determine medication discontinuation from EHR (reference standard). In claims data, discontinuation was defined by having a prescription gap larger than 15\u201390\u2009days (claims\u2010based algorithms). Sensitivity, specificity, and predictive values of claims\u2010based algorithms against the reference standard were measured. The sensitivity and specificity of 90\u2010day\u2010gap\u2010based algorithms were 0.46 and 0.79 for haloperidol, 0.41 and 0.85 for atypical APMs, 0.47 and 0.75 for BZDs, 0.33 and 0.80 for warfarin, and 0.38 and 0.87 for DOACs, respectively. The corresponding estimates for 15\u2010day\u2010gap\u2010based algorithms were 0.68 and 0.55 for haloperidol, 0.59 and 0.62 for atypical APMs, 0.71 and 0.45 for BZDs, 0.61 and 0.49 for warfarin, and 0.58 and 0.64 for DOACs, respectively. Positive predictive values were primarily affected by medication discontinuation rates and less by gap lengths. The overall accuracy of claims\u2010based discontinuation algorithms differs by medications. This study demonstrates the scalability and utility of the NLP\u2010based validation framework for multiple medications.<\/jats:p>","DOI":"10.1002\/cpt.3650","type":"journal-article","created":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T11:37:37Z","timestamp":1744112257000},"page":"138-145","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Establishing a Validation Framework of Treatment Discontinuation in Claims Data Using Natural Language Processing and Electronic Health Records"],"prefix":"10.1002","volume":"118","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5747-6806","authenticated-orcid":false,"given":"Chun\u2010Ting","family":"Yang","sequence":"first","affiliation":[{"name":"Division of Pharmacoepidemiology and Pharmacoeconomics, Department of Medicine Brigham and Women's Hospital, Harvard Medical School  Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kerry","family":"Ngan","sequence":"additional","affiliation":[{"name":"Division of Pharmacoepidemiology and Pharmacoeconomics, Department of Medicine Brigham and Women's Hospital, Harvard Medical School  Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dae Hyun","family":"Kim","sequence":"additional","affiliation":[{"name":"Hinda and Arthur Marcus Institute for Aging Research, Hebrew SeniorLife, Harvard Medical School  Boston Massachusetts USA"},{"name":"Division of Gerontology, Department of Medicine Beth Israel Deaconess Medical Center  Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Yang","sequence":"additional","affiliation":[{"name":"Division of Pharmacoepidemiology and Pharmacoeconomics, Department of Medicine Brigham and Women's Hospital, Harvard Medical School  Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Liu","sequence":"additional","affiliation":[{"name":"Division of Pharmacoepidemiology and Pharmacoeconomics, Department of Medicine Brigham and Women's Hospital, Harvard Medical School  Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kueiyu Joshua","family":"Lin","sequence":"additional","affiliation":[{"name":"Division of Pharmacoepidemiology and Pharmacoeconomics, Department of Medicine Brigham and Women's Hospital, Harvard Medical School  Boston Massachusetts USA"},{"name":"Department of Medicine Massachusetts General Hospital, Harvard Medical School  Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,4,8]]},"reference":[{"key":"e_1_2_10_1_1","first-page":"449","article-title":"Estimating medication persistency using administrative claims data","volume":"11","author":"Sikka R.","year":"2005","journal-title":"Am. J. Manag. Care"},{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1002\/pds.1230"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocv054"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2005.05.005"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ahj.2006.10.018"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1167\/iovs.07-0290"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1002\/pds.5784"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-021-01347-1"},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2018.10.005"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-biodatasci-080917-013315"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2021.26337"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1111\/dom.14512"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.1111\/jgs.18372"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40119-013-0019-y"},{"key":"e_1_2_10_15_1","doi-asserted-by":"publisher","DOI":"10.3390\/jcm11247423"},{"key":"e_1_2_10_16_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpt.2400"},{"key":"e_1_2_10_17_1","doi-asserted-by":"publisher","DOI":"10.2147\/CLEP.S232540"},{"key":"e_1_2_10_18_1","doi-asserted-by":"crossref","unstructured":"Bird S.NLTK: The natural language toolkit.Proceedings of the COLING\/ACL 2006 interactive presentation sessions; 69\u201372(2006).","DOI":"10.3115\/1225403.1225421"},{"key":"e_1_2_10_19_1","volume-title":"Natural Language Processing with Python: Analyzing Text with the Natural Language Toolkit","author":"Bird S.","year":"2009"},{"key":"e_1_2_10_20_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2023.48557"},{"key":"e_1_2_10_21_1","doi-asserted-by":"publisher","DOI":"10.1097\/YIC.0000000000000401"},{"key":"e_1_2_10_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40256-021-00501-w"},{"key":"e_1_2_10_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2010.10.004"},{"key":"e_1_2_10_24_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.309.6947.102"},{"key":"e_1_2_10_25_1","doi-asserted-by":"publisher","DOI":"10.1176\/appi.ajp.2011.11030347"},{"key":"e_1_2_10_26_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamapsychiatry.2014.3018"},{"key":"e_1_2_10_27_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.k1218"},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2023.0063"},{"key":"e_1_2_10_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.sleep.2016.04.003"},{"key":"e_1_2_10_30_1","doi-asserted-by":"publisher","DOI":"10.1055\/a-1508-8187"},{"key":"e_1_2_10_31_1","doi-asserted-by":"crossref","unstructured":"Agrawal M. Hegselmann S. Lang H. Kim Y.&Sontag D.Large language models are few\u2010shot clinical information extractors. InProceedings of the 2022 conference on empirical methods in natural language processing; 1998\u20132022(2022).","DOI":"10.18653\/v1\/2022.emnlp-main.130"}],"container-title":["Clinical Pharmacology &amp; Therapeutics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ascpt.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cpt.3650","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,9]],"date-time":"2025-08-09T07:17:17Z","timestamp":1754723837000},"score":1,"resource":{"primary":{"URL":"https:\/\/ascpt.onlinelibrary.wiley.com\/doi\/10.1002\/cpt.3650"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,8]]},"references-count":31,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["10.1002\/cpt.3650"],"URL":"https:\/\/doi.org\/10.1002\/cpt.3650","archive":["Portico"],"relation":{},"ISSN":["0009-9236","1532-6535"],"issn-type":[{"value":"0009-9236","type":"print"},{"value":"1532-6535","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,8]]},"assertion":[{"value":"2024-10-18","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-03-06","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-04-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}