{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T16:59:26Z","timestamp":1781369966527,"version":"3.54.1"},"reference-count":30,"publisher":"Wiley","issue":"9","license":[{"start":{"date-parts":[[2021,8,4]],"date-time":"2021-08-04T00:00:00Z","timestamp":1628035200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Clinical Cardiology"],"published-print":{"date-parts":[[2021,9]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:label\/><jats:p><jats:bold>Objective:<\/jats:bold> Accurate ascertainment of comorbidities is paramount in clinical research. While manual adjudication is labor\u2010intensive and expensive, the adoption of electronic health records enables computational analysis of free\u2010text documentation using natural language processing (NLP) tools.<\/jats:p><jats:p><jats:bold>Hypothesis:<\/jats:bold> We sought to develop highly accurate NLP modules to assess for the presence of five key cardiovascular comorbidities in a large electronic health record system.<\/jats:p><jats:p><jats:bold>Methods:<\/jats:bold> One\u2010thousand clinical notes were randomly selected from a cardiovascular registry at Mass General Brigham. Trained physicians manually adjudicated these notes for the following five diagnostic comorbidities: hypertension, dyslipidemia, diabetes, coronary artery disease, and stroke\/transient ischemic attack. Using the open\u2010source Canary NLP system, five separate NLP modules were designed based on 800 \u201ctraining\u2010set\u201d notes and validated on 200 \u201ctest\u2010set\u201d notes.<\/jats:p><jats:p><jats:bold>Results:<\/jats:bold> Across the five NLP modules, the sentence\u2010level and note\u2010level sensitivity, specificity, and positive predictive value was always greater than 85% and was most often greater than 90%. Accuracy tended to be highest for conditions with greater diagnostic clarity (e.g. diabetes and hypertension) and slightly lower for conditions whose greater diagnostic challenges (e.g. myocardial infarction and embolic stroke) may lead to less definitive documentation.<\/jats:p><jats:p><jats:bold>Conclusion:<\/jats:bold> We designed five open\u2010source and highly accurate NLP modules that can be used to assess for the presence of important cardiovascular comorbidities in free\u2010text health records. These modules have been placed in the public domain and can be used for clinical research, trial recruitment and population management at any institution as well as serve as the basis for further development of cardiovascular NLP tools.<\/jats:p><\/jats:sec>","DOI":"10.1002\/clc.23687","type":"journal-article","created":{"date-parts":[[2021,8,4]],"date-time":"2021-08-04T12:41:45Z","timestamp":1628080905000},"page":"1296-1304","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":33,"title":["Natural language processing for the assessment of cardiovascular disease comorbidities: The <scp>cardio\u2010Canary<\/scp> comorbidity project"],"prefix":"10.1002","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0724-9779","authenticated-orcid":false,"given":"Adam N.","family":"Berman","sequence":"first","affiliation":[{"name":"Cardiovascular Division, Department of Medicine, Brigham and Women's Hospital Harvard Medical School  Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David W.","family":"Biery","sequence":"additional","affiliation":[{"name":"Cardiovascular Division, Department of Medicine, Brigham and Women's Hospital Harvard Medical School  Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Curtis","family":"Ginder","sequence":"additional","affiliation":[{"name":"Department of Medicine, Brigham and Women's Hospital Harvard Medical School  Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olivia L.","family":"Hulme","sequence":"additional","affiliation":[{"name":"Department of Medicine, Brigham and Women's Hospital Harvard Medical School  Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Marcusa","sequence":"additional","affiliation":[{"name":"Department of Medicine, Brigham and Women's Hospital Harvard Medical School  Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Orly","family":"Leiva","sequence":"additional","affiliation":[{"name":"Department of Medicine, Brigham and Women's Hospital Harvard Medical School  Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wanda Y.","family":"Wu","sequence":"additional","affiliation":[{"name":"Cardiovascular Division, Department of Medicine, Brigham and Women's Hospital Harvard Medical School  Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicholas","family":"Cardin","sequence":"additional","affiliation":[{"name":"Division of Endocrinology, Department of Medicine, Brigham and Women's Hospital Harvard Medical School  Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0572-912X","authenticated-orcid":false,"given":"Jon","family":"Hainer","sequence":"additional","affiliation":[{"name":"Department of Radiology, Brigham and Women's Hospital Harvard Medical School  Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1278-6245","authenticated-orcid":false,"given":"Deepak L.","family":"Bhatt","sequence":"additional","affiliation":[{"name":"Cardiovascular Division, Department of Medicine, Brigham and Women's Hospital Harvard Medical School  Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marcelo F.","family":"Di Carli","sequence":"additional","affiliation":[{"name":"Cardiovascular Division, Department of Medicine, Brigham and Women's Hospital Harvard Medical School  Boston Massachusetts USA"},{"name":"Department of Radiology, Brigham and Women's Hospital Harvard Medical School  Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"Turchin","sequence":"additional","affiliation":[{"name":"Division of Endocrinology, Department of Medicine, Brigham and Women's Hospital Harvard Medical School  Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ron","family":"Blankstein","sequence":"additional","affiliation":[{"name":"Cardiovascular Division, Department of Medicine, Brigham and Women's Hospital Harvard Medical School  Boston Massachusetts USA"},{"name":"Department of Radiology, Brigham and Women's Hospital Harvard Medical School  Boston Massachusetts USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2021,8,4]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1093\/aje\/154.9.854"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1097\/01.mlr.0000160417.39497.a9"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1002\/pds.2313"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1177\/106286060401900504"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2458-13-16"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cjca.2013.07.676"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1097\/00001888-199908000-00012"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2011.1219"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2017.18391"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2005.11.004"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1136\/amiajnl-2011-000464"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamaoncol.2016.0213"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.annemergmed.2013.02.001"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2016.07.012"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1136\/amiajnl-2014-002945"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1186\/1472-6947-12-34"},{"key":"e_1_2_8_18_1","first-page":"1270","article-title":"Structured vs unstructured: factors affecting adverse drug reaction documentation in an EMR repository","volume":"2011","author":"Skentzos S","year":"2011","journal-title":"AMIA Annu Symp Proc"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1136\/amiajnl-2012-000928"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.7326\/M16-0838"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2015.08.002"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1136\/amiajnl-2013-001889"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1001\/jamacardio.2016.3826"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2019.103208"},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2008.08.010"},{"key":"e_1_2_8_26_1","doi-asserted-by":"publisher","DOI":"10.4338\/ACI-2017-01-IE-0018"},{"key":"e_1_2_8_27_1","unstructured":"TurchinA.Canary NLP Tool Web site.http:\/\/canary.bwh.harvard.edu. Accessed May 11 2020."},{"key":"e_1_2_8_28_1","doi-asserted-by":"publisher","DOI":"10.7326\/0003-4819-158-7-201304020-00004"},{"key":"e_1_2_8_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2019.103306"},{"key":"e_1_2_8_30_1","doi-asserted-by":"publisher","DOI":"10.1177\/19322968211000831"},{"key":"e_1_2_8_31_1","unstructured":"Canary NLP Tool Library.https:\/\/canary.bwh.harvard.edu\/library\/. Accessed April 25 2021."}],"container-title":["Clinical Cardiology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/clc.23687","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/clc.23687","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/clc.23687","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,29]],"date-time":"2023-08-29T22:06:19Z","timestamp":1693346779000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/clc.23687"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,4]]},"references-count":30,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2021,9]]}},"alternative-id":["10.1002\/clc.23687"],"URL":"https:\/\/doi.org\/10.1002\/clc.23687","archive":["Portico"],"relation":{},"ISSN":["0160-9289","1932-8737"],"issn-type":[{"value":"0160-9289","type":"print"},{"value":"1932-8737","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8,4]]},"assertion":[{"value":"2021-05-10","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-06-24","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-08-04","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}