{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T02:02:38Z","timestamp":1784512958099,"version":"3.55.0"},"reference-count":14,"publisher":"Wiley","issue":"7","license":[{"start":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T00:00:00Z","timestamp":1781568000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T00:00:00Z","timestamp":1781568000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Pharmacoepidemiology and Drug"],"published-print":{"date-parts":[[2026,7]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>Studies based on electronic health records (EHR) often rely on structured data, which may incompletely capture important clinical phenotypes in EHR notes. The purpose of this study was to assess two natural language processing (NLP) tools to extract phenotypes from unstructured EHR notes, and to evaluate the added value of integrating NLP\u2010derived phenotypes with structured EHR data at a health system scale.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective study is based on inpatient and outpatient EHR data from the Mass General Brigham healthcare system between January 1, 2019 and December 31, 2020. Two established rule\u2010based NLP tools were applied to extract smoking and obesity information from 19\u2009215\u2009303 clinical notes of 503\u2009025 patients. NLP performance was evaluated through a manual review of stratified samples. Phenotype prevalence was estimated using structured EHR data alone and compared with prevalence estimates obtained by supplementing structured data with NLP\u2010derived features.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Both NLP tools exhibited high performance, with both accuracy and the F1 score of 0.99 for smoking, and 0.92 and 0.91 for obesity, respectively. The combination of NLP and structured data identified 220\u2009714 patients (43.88%) with smoking, compared with 170\u2009396 patients (33.87%) identified using structured data alone, representing a 29.5% relative increase. For obesity, NLP identified 121\u2009360 patients (24.13%) from EHR notes, and 169\u2009905 patients (33.78%) were documented in structured data; the inclusion of NLP\u2010derived features contributed an additional 32\u2009823 patients, corresponding to a 19.3% relative increase.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>NLP\u2010derived phenotypes from unstructured EHR notes substantially improve patient identification for both smoking and obesity compared with structured EHR data alone at scale.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/pds.70415","type":"journal-article","created":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T13:34:18Z","timestamp":1781616858000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Using Natural Language Processing of Clinical Notes to Supplement Structured Electronic Health Record Data for Phenotyping Smoking and Obesity in a Healthcare System"],"prefix":"10.1002","volume":"35","author":[{"given":"Jie","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"},{"name":"Kempner Institute for the Study of Natural and Artificial Intelligence, Harvard University  Massachusetts USA"},{"name":"Broad Institute of MIT and Harvard  Cambridge Massachusetts USA"},{"name":"Harvard Data Science Initiative, Harvard University  Cambridge Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0739-0390","authenticated-orcid":false,"given":"Bowen","family":"Gu","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":"Haritha","family":"Pillai","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":"Joyce","family":"Lii","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":"David","family":"Cronkite","sequence":"additional","affiliation":[{"name":"Kaiser Permanente Washington Health Research Institute  Seattle WA USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Keith A.","family":"Marsolo","sequence":"additional","affiliation":[{"name":"Department of Population Health Sciences Duke University School of Medicine  Durham North Carolina USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rishi J.","family":"Desai","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"}]}],"member":"311","published-online":{"date-parts":[[2026,6,16]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40264-023-01325-0"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1002\/pds.5548"},{"key":"e_1_2_10_4_1","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocw168"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1002\/pds.2139"},{"key":"e_1_2_10_6_1","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocad066"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2025.104882"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2025.109855"},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.1002\/pds.70028"},{"key":"e_1_2_10_10_1","unstructured":"\u201cFE5 Variables with Konsepy NLP \u201daccessed August 27 2025 https:\/\/github.com\/kpwhri\/fe5_konsepy."},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1136\/jamia.2009.001560"},{"key":"e_1_2_10_12_1","doi-asserted-by":"crossref","unstructured":"J.Wu B.Gu R.Zhou et\u00a0al. \u201cBRIDGE: Benchmarking Large Language Models for Understanding Real\u2010World Clinical Practice Text \u201darXiv Preprint arXiv:250419467. 2025.","DOI":"10.1038\/s41551-026-01719-2"},{"key":"e_1_2_10_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2025.112049"},{"key":"e_1_2_10_14_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-025-02470-z"},{"key":"e_1_2_10_15_1","first-page":"74","volume-title":"NCRF++: An Open\u2010Source Neural Sequence Labeling Toolkit","author":"Yang J.","year":"2018"}],"container-title":["Pharmacoepidemiology and Drug Safety"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/pds.70415","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/pds.70415","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/pds.70415","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T01:41:40Z","timestamp":1784511700000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/pds.70415"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,16]]},"references-count":14,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,7]]}},"alternative-id":["10.1002\/pds.70415"],"URL":"https:\/\/doi.org\/10.1002\/pds.70415","archive":["Portico"],"relation":{},"ISSN":["1053-8569","1099-1557"],"issn-type":[{"value":"1053-8569","type":"print"},{"value":"1099-1557","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,16]]},"assertion":[{"value":"2026-01-18","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-07","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70415"}}