Cargando…

A novel method of adverse event detection can accurately identify venous thromboembolisms (VTEs) from narrative electronic health record data

Background Venous thromboembolisms (VTEs), which include deep vein thrombosis (DVT) and pulmonary embolism (PE), are associated with significant mortality, morbidity, and cost in hospitalized patients. To evaluate the success of preventive measures, accurate and efficient methods for monitoring VTE...

Descripción completa

Detalles Bibliográficos
Autores principales: Rochefort, Christian M, Verma, Aman D, Eguale, Tewodros, Lee, Todd C, Buckeridge, David L
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Oxford University Press 2015
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4433368/
https://www.ncbi.nlm.nih.gov/pubmed/25332356
http://dx.doi.org/10.1136/amiajnl-2014-002768
_version_ 1782371635434618880
author Rochefort, Christian M
Verma, Aman D
Eguale, Tewodros
Lee, Todd C
Buckeridge, David L
author_facet Rochefort, Christian M
Verma, Aman D
Eguale, Tewodros
Lee, Todd C
Buckeridge, David L
author_sort Rochefort, Christian M
collection PubMed
description Background Venous thromboembolisms (VTEs), which include deep vein thrombosis (DVT) and pulmonary embolism (PE), are associated with significant mortality, morbidity, and cost in hospitalized patients. To evaluate the success of preventive measures, accurate and efficient methods for monitoring VTE rates are needed. Therefore, we sought to determine the accuracy of statistical natural language processing (NLP) for identifying DVT and PE from electronic health record data. Methods We randomly sampled 2000 narrative radiology reports from patients with a suspected DVT/PE in Montreal (Canada) between 2008 and 2012. We manually identified DVT/PE within each report, which served as our reference standard. Using a bag-of-words approach, we trained 10 alternative support vector machine (SVM) models predicting DVT, and 10 predicting PE. SVM training and testing was performed with nested 10-fold cross-validation, and the average accuracy of each model was measured and compared. Results On manual review, 324 (16.2%) reports were DVT-positive and 154 (7.7%) were PE-positive. The best DVT model achieved an average sensitivity of 0.80 (95% CI 0.76 to 0.85), specificity of 0.98 (98% CI 0.97 to 0.99), positive predictive value (PPV) of 0.89 (95% CI 0.85 to 0.93), and an area under the curve (AUC) of 0.98 (95% CI 0.97 to 0.99). The best PE model achieved sensitivity of 0.79 (95% CI 0.73 to 0.85), specificity of 0.99 (95% CI 0.98 to 0.99), PPV of 0.84 (95% CI 0.75 to 0.92), and AUC of 0.99 (95% CI 0.98 to 1.00). Conclusions Statistical NLP can accurately identify VTE from narrative radiology reports.
format Online
Article
Text
id pubmed-4433368
institution National Center for Biotechnology Information
language English
publishDate 2015
publisher Oxford University Press
record_format MEDLINE/PubMed
spelling pubmed-44333682016-01-01 A novel method of adverse event detection can accurately identify venous thromboembolisms (VTEs) from narrative electronic health record data Rochefort, Christian M Verma, Aman D Eguale, Tewodros Lee, Todd C Buckeridge, David L J Am Med Inform Assoc Research and Applications Background Venous thromboembolisms (VTEs), which include deep vein thrombosis (DVT) and pulmonary embolism (PE), are associated with significant mortality, morbidity, and cost in hospitalized patients. To evaluate the success of preventive measures, accurate and efficient methods for monitoring VTE rates are needed. Therefore, we sought to determine the accuracy of statistical natural language processing (NLP) for identifying DVT and PE from electronic health record data. Methods We randomly sampled 2000 narrative radiology reports from patients with a suspected DVT/PE in Montreal (Canada) between 2008 and 2012. We manually identified DVT/PE within each report, which served as our reference standard. Using a bag-of-words approach, we trained 10 alternative support vector machine (SVM) models predicting DVT, and 10 predicting PE. SVM training and testing was performed with nested 10-fold cross-validation, and the average accuracy of each model was measured and compared. Results On manual review, 324 (16.2%) reports were DVT-positive and 154 (7.7%) were PE-positive. The best DVT model achieved an average sensitivity of 0.80 (95% CI 0.76 to 0.85), specificity of 0.98 (98% CI 0.97 to 0.99), positive predictive value (PPV) of 0.89 (95% CI 0.85 to 0.93), and an area under the curve (AUC) of 0.98 (95% CI 0.97 to 0.99). The best PE model achieved sensitivity of 0.79 (95% CI 0.73 to 0.85), specificity of 0.99 (95% CI 0.98 to 0.99), PPV of 0.84 (95% CI 0.75 to 0.92), and AUC of 0.99 (95% CI 0.98 to 1.00). Conclusions Statistical NLP can accurately identify VTE from narrative radiology reports. Oxford University Press 2015-01 2014-10-20 /pmc/articles/PMC4433368/ /pubmed/25332356 http://dx.doi.org/10.1136/amiajnl-2014-002768 Text en © The Author 2014. Published by Oxford University Press on behalf of the American Medical Informatics Association. http://creativecommons.org/licenses/by-nc/4.0 This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/4.0/), which permits non-commercial re-use, distribution, and reproduction in any medium, provided the original work is properly cited. For commercial re-use, please contact journals.permissions@oup.comFor numbered affiliations see end of article.
spellingShingle Research and Applications
Rochefort, Christian M
Verma, Aman D
Eguale, Tewodros
Lee, Todd C
Buckeridge, David L
A novel method of adverse event detection can accurately identify venous thromboembolisms (VTEs) from narrative electronic health record data
title A novel method of adverse event detection can accurately identify venous thromboembolisms (VTEs) from narrative electronic health record data
title_full A novel method of adverse event detection can accurately identify venous thromboembolisms (VTEs) from narrative electronic health record data
title_fullStr A novel method of adverse event detection can accurately identify venous thromboembolisms (VTEs) from narrative electronic health record data
title_full_unstemmed A novel method of adverse event detection can accurately identify venous thromboembolisms (VTEs) from narrative electronic health record data
title_short A novel method of adverse event detection can accurately identify venous thromboembolisms (VTEs) from narrative electronic health record data
title_sort novel method of adverse event detection can accurately identify venous thromboembolisms (vtes) from narrative electronic health record data
topic Research and Applications
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4433368/
https://www.ncbi.nlm.nih.gov/pubmed/25332356
http://dx.doi.org/10.1136/amiajnl-2014-002768
work_keys_str_mv AT rochefortchristianm anovelmethodofadverseeventdetectioncanaccuratelyidentifyvenousthromboembolismsvtesfromnarrativeelectronichealthrecorddata
AT vermaamand anovelmethodofadverseeventdetectioncanaccuratelyidentifyvenousthromboembolismsvtesfromnarrativeelectronichealthrecorddata
AT egualetewodros anovelmethodofadverseeventdetectioncanaccuratelyidentifyvenousthromboembolismsvtesfromnarrativeelectronichealthrecorddata
AT leetoddc anovelmethodofadverseeventdetectioncanaccuratelyidentifyvenousthromboembolismsvtesfromnarrativeelectronichealthrecorddata
AT buckeridgedavidl anovelmethodofadverseeventdetectioncanaccuratelyidentifyvenousthromboembolismsvtesfromnarrativeelectronichealthrecorddata
AT rochefortchristianm novelmethodofadverseeventdetectioncanaccuratelyidentifyvenousthromboembolismsvtesfromnarrativeelectronichealthrecorddata
AT vermaamand novelmethodofadverseeventdetectioncanaccuratelyidentifyvenousthromboembolismsvtesfromnarrativeelectronichealthrecorddata
AT egualetewodros novelmethodofadverseeventdetectioncanaccuratelyidentifyvenousthromboembolismsvtesfromnarrativeelectronichealthrecorddata
AT leetoddc novelmethodofadverseeventdetectioncanaccuratelyidentifyvenousthromboembolismsvtesfromnarrativeelectronichealthrecorddata
AT buckeridgedavidl novelmethodofadverseeventdetectioncanaccuratelyidentifyvenousthromboembolismsvtesfromnarrativeelectronichealthrecorddata