Automatic computation of CHA2DS2-VASc score: information extraction from clinical texts for thromboembolism risk assessment
The CHA2DS2-VASc score is a 10-point scale which allows cardiologists to easily identify potential stroke risk for patients with non-valvular fibrillation. In this article, we present a system based on natural language processing (lexicon and linguistic modules), including negation and speculation h...
Gespeichert in:
| Veröffentlicht in: | AMIA ... Annual Symposium proceedings 2011, Vol.2011, p.501-10 |
|---|---|
| Hauptverfasser: | , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 10 |
|---|---|
| container_issue | |
| container_start_page | 501 |
| container_title | AMIA ... Annual Symposium proceedings |
| container_volume | 2011 |
| creator | Grouin, Cyril Deléger, Louise Rosier, Arnaud Temal, Lynda Dameron, Olivier Van Hille, Pascal Burgun, Anita Zweigenbaum, Pierre |
| description | The CHA2DS2-VASc score is a 10-point scale which allows cardiologists to easily identify potential stroke risk for patients with non-valvular fibrillation. In this article, we present a system based on natural language processing (lexicon and linguistic modules), including negation and speculation handling, which extracts medical concepts from French clinical records and uses them as criteria to compute the CHA2DS2-VASc score. We evaluate this system by comparing its computed criteria with those obtained by human reading of the same clinical texts, and by assessing the impact of the observed differences on the resulting CHA2DS2-VASc scores. Given 21 patient records, 168 instances of criteria were computed, with an accuracy of 97.6%, and the accuracy of the 21 CHA2DS2-VASc scores was 85.7%. All differences in scores trigger the same alert, which means that system performance on this test set yields similar results to human reading of the texts. |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_3243195</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>912643011</sourcerecordid><originalsourceid>FETCH-LOGICAL-h214t-8bed3aca0bae68e11c1adb83a04d911b381195af67c1495117263ac268dd13c43</originalsourceid><addsrcrecordid>eNpdkV1LwzAUhosobk7_guROvCjkq23qhVDmx4SBF1PxrqRpaqNNM5N0KP55MzdFvQh5Oe-b55xDdqIxSpI8pjBLd4POKY6TPHscRQfOPUNIs4Sl-9EIY5QnCNJx9FEM3mjulQDC6OXggzQ9MA2Yzgp8scDxQ7EQwAlj5RlQfWOs3kTkm7dcfMnGGg1Ep3oleAd8cBwIQeDbYFRGhtMpp4FV7gVw56RzWvb-MNpreOfk0faeRPdXl3fTWTy_vb6ZFvO4xYj6mFWyJlxwWHGZMomQQLyuGOGQ1jlCFWEobMObNBOIhrVQhtOQxymra0QEJZPofMNdDpWWtQitLe_KpVWa2_fScFX-dXrVlk9mVRJMSUAHwOkG0P57Nivm5boGYUZZwtgKhezJtpk1r4N0vtTKCdl1vJdmcGWOcEoJROvk8e-xfsDfn0M-AQRnjuY</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>912643011</pqid></control><display><type>article</type><title>Automatic computation of CHA2DS2-VASc score: information extraction from clinical texts for thromboembolism risk assessment</title><source>MEDLINE</source><source>EZB-FREE-00999 freely available EZB journals</source><source>PubMed Central</source><creator>Grouin, Cyril ; Deléger, Louise ; Rosier, Arnaud ; Temal, Lynda ; Dameron, Olivier ; Van Hille, Pascal ; Burgun, Anita ; Zweigenbaum, Pierre</creator><creatorcontrib>Grouin, Cyril ; Deléger, Louise ; Rosier, Arnaud ; Temal, Lynda ; Dameron, Olivier ; Van Hille, Pascal ; Burgun, Anita ; Zweigenbaum, Pierre</creatorcontrib><description>The CHA2DS2-VASc score is a 10-point scale which allows cardiologists to easily identify potential stroke risk for patients with non-valvular fibrillation. In this article, we present a system based on natural language processing (lexicon and linguistic modules), including negation and speculation handling, which extracts medical concepts from French clinical records and uses them as criteria to compute the CHA2DS2-VASc score. We evaluate this system by comparing its computed criteria with those obtained by human reading of the same clinical texts, and by assessing the impact of the observed differences on the resulting CHA2DS2-VASc scores. Given 21 patient records, 168 instances of criteria were computed, with an accuracy of 97.6%, and the accuracy of the 21 CHA2DS2-VASc scores was 85.7%. All differences in scores trigger the same alert, which means that system performance on this test set yields similar results to human reading of the texts.</description><identifier>ISSN: 1942-597X</identifier><identifier>EISSN: 1559-4076</identifier><identifier>PMID: 22195104</identifier><language>eng</language><publisher>United States: American Medical Informatics Association</publisher><subject>Atrial Fibrillation - complications ; Cardiology ; Electronic Health Records ; Human health and pathology ; Humans ; Language ; Life Sciences ; Natural Language Processing ; Risk Assessment - methods ; Stroke - etiology ; Thromboembolism - etiology</subject><ispartof>AMIA ... Annual Symposium proceedings, 2011, Vol.2011, p.501-10</ispartof><rights>Distributed under a Creative Commons Attribution 4.0 International License</rights><rights>2011 AMIA - All rights reserved. 2011</rights><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><orcidid>0000-0003-4556-5702 ; 0000-0001-5809-188X ; 0000-0001-6855-4366 ; 0000-0003-1399-4828 ; 0000-0001-8410-4808</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC3243195/pdf/$$EPDF$$P50$$Gpubmedcentral$$H</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC3243195/$$EHTML$$P50$$Gpubmedcentral$$H</linktohtml><link.rule.ids>230,314,727,780,784,885,4024,53791,53793</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/22195104$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink><backlink>$$Uhttps://hal.science/hal-00748588$$DView record in HAL$$Hfree_for_read</backlink></links><search><creatorcontrib>Grouin, Cyril</creatorcontrib><creatorcontrib>Deléger, Louise</creatorcontrib><creatorcontrib>Rosier, Arnaud</creatorcontrib><creatorcontrib>Temal, Lynda</creatorcontrib><creatorcontrib>Dameron, Olivier</creatorcontrib><creatorcontrib>Van Hille, Pascal</creatorcontrib><creatorcontrib>Burgun, Anita</creatorcontrib><creatorcontrib>Zweigenbaum, Pierre</creatorcontrib><title>Automatic computation of CHA2DS2-VASc score: information extraction from clinical texts for thromboembolism risk assessment</title><title>AMIA ... Annual Symposium proceedings</title><addtitle>AMIA Annu Symp Proc</addtitle><description>The CHA2DS2-VASc score is a 10-point scale which allows cardiologists to easily identify potential stroke risk for patients with non-valvular fibrillation. In this article, we present a system based on natural language processing (lexicon and linguistic modules), including negation and speculation handling, which extracts medical concepts from French clinical records and uses them as criteria to compute the CHA2DS2-VASc score. We evaluate this system by comparing its computed criteria with those obtained by human reading of the same clinical texts, and by assessing the impact of the observed differences on the resulting CHA2DS2-VASc scores. Given 21 patient records, 168 instances of criteria were computed, with an accuracy of 97.6%, and the accuracy of the 21 CHA2DS2-VASc scores was 85.7%. All differences in scores trigger the same alert, which means that system performance on this test set yields similar results to human reading of the texts.</description><subject>Atrial Fibrillation - complications</subject><subject>Cardiology</subject><subject>Electronic Health Records</subject><subject>Human health and pathology</subject><subject>Humans</subject><subject>Language</subject><subject>Life Sciences</subject><subject>Natural Language Processing</subject><subject>Risk Assessment - methods</subject><subject>Stroke - etiology</subject><subject>Thromboembolism - etiology</subject><issn>1942-597X</issn><issn>1559-4076</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2011</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNpdkV1LwzAUhosobk7_guROvCjkq23qhVDmx4SBF1PxrqRpaqNNM5N0KP55MzdFvQh5Oe-b55xDdqIxSpI8pjBLd4POKY6TPHscRQfOPUNIs4Sl-9EIY5QnCNJx9FEM3mjulQDC6OXggzQ9MA2Yzgp8scDxQ7EQwAlj5RlQfWOs3kTkm7dcfMnGGg1Ep3oleAd8cBwIQeDbYFRGhtMpp4FV7gVw56RzWvb-MNpreOfk0faeRPdXl3fTWTy_vb6ZFvO4xYj6mFWyJlxwWHGZMomQQLyuGOGQ1jlCFWEobMObNBOIhrVQhtOQxymra0QEJZPofMNdDpWWtQitLe_KpVWa2_fScFX-dXrVlk9mVRJMSUAHwOkG0P57Nivm5boGYUZZwtgKhezJtpk1r4N0vtTKCdl1vJdmcGWOcEoJROvk8e-xfsDfn0M-AQRnjuY</recordid><startdate>2011</startdate><enddate>2011</enddate><creator>Grouin, Cyril</creator><creator>Deléger, Louise</creator><creator>Rosier, Arnaud</creator><creator>Temal, Lynda</creator><creator>Dameron, Olivier</creator><creator>Van Hille, Pascal</creator><creator>Burgun, Anita</creator><creator>Zweigenbaum, Pierre</creator><general>American Medical Informatics Association</general><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>7X8</scope><scope>1XC</scope><scope>5PM</scope><orcidid>https://orcid.org/0000-0003-4556-5702</orcidid><orcidid>https://orcid.org/0000-0001-5809-188X</orcidid><orcidid>https://orcid.org/0000-0001-6855-4366</orcidid><orcidid>https://orcid.org/0000-0003-1399-4828</orcidid><orcidid>https://orcid.org/0000-0001-8410-4808</orcidid></search><sort><creationdate>2011</creationdate><title>Automatic computation of CHA2DS2-VASc score: information extraction from clinical texts for thromboembolism risk assessment</title><author>Grouin, Cyril ; Deléger, Louise ; Rosier, Arnaud ; Temal, Lynda ; Dameron, Olivier ; Van Hille, Pascal ; Burgun, Anita ; Zweigenbaum, Pierre</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-h214t-8bed3aca0bae68e11c1adb83a04d911b381195af67c1495117263ac268dd13c43</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2011</creationdate><topic>Atrial Fibrillation - complications</topic><topic>Cardiology</topic><topic>Electronic Health Records</topic><topic>Human health and pathology</topic><topic>Humans</topic><topic>Language</topic><topic>Life Sciences</topic><topic>Natural Language Processing</topic><topic>Risk Assessment - methods</topic><topic>Stroke - etiology</topic><topic>Thromboembolism - etiology</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Grouin, Cyril</creatorcontrib><creatorcontrib>Deléger, Louise</creatorcontrib><creatorcontrib>Rosier, Arnaud</creatorcontrib><creatorcontrib>Temal, Lynda</creatorcontrib><creatorcontrib>Dameron, Olivier</creatorcontrib><creatorcontrib>Van Hille, Pascal</creatorcontrib><creatorcontrib>Burgun, Anita</creatorcontrib><creatorcontrib>Zweigenbaum, Pierre</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>MEDLINE - Academic</collection><collection>Hyper Article en Ligne (HAL)</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>AMIA ... Annual Symposium proceedings</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Grouin, Cyril</au><au>Deléger, Louise</au><au>Rosier, Arnaud</au><au>Temal, Lynda</au><au>Dameron, Olivier</au><au>Van Hille, Pascal</au><au>Burgun, Anita</au><au>Zweigenbaum, Pierre</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Automatic computation of CHA2DS2-VASc score: information extraction from clinical texts for thromboembolism risk assessment</atitle><jtitle>AMIA ... Annual Symposium proceedings</jtitle><addtitle>AMIA Annu Symp Proc</addtitle><date>2011</date><risdate>2011</risdate><volume>2011</volume><spage>501</spage><epage>10</epage><pages>501-10</pages><issn>1942-597X</issn><eissn>1559-4076</eissn><abstract>The CHA2DS2-VASc score is a 10-point scale which allows cardiologists to easily identify potential stroke risk for patients with non-valvular fibrillation. In this article, we present a system based on natural language processing (lexicon and linguistic modules), including negation and speculation handling, which extracts medical concepts from French clinical records and uses them as criteria to compute the CHA2DS2-VASc score. We evaluate this system by comparing its computed criteria with those obtained by human reading of the same clinical texts, and by assessing the impact of the observed differences on the resulting CHA2DS2-VASc scores. Given 21 patient records, 168 instances of criteria were computed, with an accuracy of 97.6%, and the accuracy of the 21 CHA2DS2-VASc scores was 85.7%. All differences in scores trigger the same alert, which means that system performance on this test set yields similar results to human reading of the texts.</abstract><cop>United States</cop><pub>American Medical Informatics Association</pub><pmid>22195104</pmid><tpages>-490</tpages><orcidid>https://orcid.org/0000-0003-4556-5702</orcidid><orcidid>https://orcid.org/0000-0001-5809-188X</orcidid><orcidid>https://orcid.org/0000-0001-6855-4366</orcidid><orcidid>https://orcid.org/0000-0003-1399-4828</orcidid><orcidid>https://orcid.org/0000-0001-8410-4808</orcidid></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1942-597X |
| ispartof | AMIA ... Annual Symposium proceedings, 2011, Vol.2011, p.501-10 |
| issn | 1942-597X 1559-4076 |
| language | eng |
| recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_3243195 |
| source | MEDLINE; EZB-FREE-00999 freely available EZB journals; PubMed Central |
| subjects | Atrial Fibrillation - complications Cardiology Electronic Health Records Human health and pathology Humans Language Life Sciences Natural Language Processing Risk Assessment - methods Stroke - etiology Thromboembolism - etiology |
| title | Automatic computation of CHA2DS2-VASc score: information extraction from clinical texts for thromboembolism risk assessment |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T10%3A55%3A37IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Automatic%20computation%20of%20CHA2DS2-VASc%20score:%20information%20extraction%20from%20clinical%20texts%20for%20thromboembolism%20risk%20assessment&rft.jtitle=AMIA%20...%20Annual%20Symposium%20proceedings&rft.au=Grouin,%20Cyril&rft.date=2011&rft.volume=2011&rft.spage=501&rft.epage=10&rft.pages=501-10&rft.issn=1942-597X&rft.eissn=1559-4076&rft_id=info:doi/&rft_dat=%3Cproquest_pubme%3E912643011%3C/proquest_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=912643011&rft_id=info:pmid/22195104&rfr_iscdi=true |