Cargando…
Natural Language Processing Improves Detection of Nonsevere Hypoglycemia in Medical Records Versus Coding Alone in Patients With Type 2 Diabetes but Does Not Improve Prediction of Severe Hypoglycemia Events: An Analysis Using the Electronic Medical Record in a Large Health System
OBJECTIVE: To determine if natural language processing (NLP) improves detection of nonsevere hypoglycemia (NSH) in patients with type 2 diabetes and no NSH documentation by diagnosis codes and to measure if NLP detection improves the prediction of future severe hypoglycemia (SH). RESEARCH DESIGN AND...
Autores principales: | , , , , , , , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
American Diabetes Association
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7372042/ https://www.ncbi.nlm.nih.gov/pubmed/32414887 http://dx.doi.org/10.2337/dc19-1791 |
_version_ | 1783561232310075392 |
---|---|
author | Misra-Hebert, Anita D. Milinovich, Alex Zajichek, Alex Ji, Xinge Hobbs, Todd D. Weng, Wayne Petraro, Paul Kong, Sheldon X. Mocarski, Michelle Ganguly, Rahul Bauman, Janine M. Pantalone, Kevin M. Zimmerman, Robert S. Kattan, Michael W. |
author_facet | Misra-Hebert, Anita D. Milinovich, Alex Zajichek, Alex Ji, Xinge Hobbs, Todd D. Weng, Wayne Petraro, Paul Kong, Sheldon X. Mocarski, Michelle Ganguly, Rahul Bauman, Janine M. Pantalone, Kevin M. Zimmerman, Robert S. Kattan, Michael W. |
author_sort | Misra-Hebert, Anita D. |
collection | PubMed |
description | OBJECTIVE: To determine if natural language processing (NLP) improves detection of nonsevere hypoglycemia (NSH) in patients with type 2 diabetes and no NSH documentation by diagnosis codes and to measure if NLP detection improves the prediction of future severe hypoglycemia (SH). RESEARCH DESIGN AND METHODS: From 2005 to 2017, we identified NSH events by diagnosis codes and NLP. We then built an SH prediction model. RESULTS: There were 204,517 patients with type 2 diabetes and no diagnosis codes for NSH. Evidence of NSH was found in 7,035 (3.4%) of patients using NLP. We reviewed 1,200 of the NLP-detected NSH notes and confirmed 93% to have NSH. The SH prediction model (C-statistic 0.806) showed increased risk with NSH (hazard ratio 4.44; P < 0.001). However, the model with NLP did not improve SH prediction compared with diagnosis code–only NSH. CONCLUSIONS: Detection of NSH improved with NLP in patients with type 2 diabetes without improving SH prediction. |
format | Online Article Text |
id | pubmed-7372042 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2020 |
publisher | American Diabetes Association |
record_format | MEDLINE/PubMed |
spelling | pubmed-73720422020-07-24 Natural Language Processing Improves Detection of Nonsevere Hypoglycemia in Medical Records Versus Coding Alone in Patients With Type 2 Diabetes but Does Not Improve Prediction of Severe Hypoglycemia Events: An Analysis Using the Electronic Medical Record in a Large Health System Misra-Hebert, Anita D. Milinovich, Alex Zajichek, Alex Ji, Xinge Hobbs, Todd D. Weng, Wayne Petraro, Paul Kong, Sheldon X. Mocarski, Michelle Ganguly, Rahul Bauman, Janine M. Pantalone, Kevin M. Zimmerman, Robert S. Kattan, Michael W. Diabetes Care Novel Communications in Diabetes OBJECTIVE: To determine if natural language processing (NLP) improves detection of nonsevere hypoglycemia (NSH) in patients with type 2 diabetes and no NSH documentation by diagnosis codes and to measure if NLP detection improves the prediction of future severe hypoglycemia (SH). RESEARCH DESIGN AND METHODS: From 2005 to 2017, we identified NSH events by diagnosis codes and NLP. We then built an SH prediction model. RESULTS: There were 204,517 patients with type 2 diabetes and no diagnosis codes for NSH. Evidence of NSH was found in 7,035 (3.4%) of patients using NLP. We reviewed 1,200 of the NLP-detected NSH notes and confirmed 93% to have NSH. The SH prediction model (C-statistic 0.806) showed increased risk with NSH (hazard ratio 4.44; P < 0.001). However, the model with NLP did not improve SH prediction compared with diagnosis code–only NSH. CONCLUSIONS: Detection of NSH improved with NLP in patients with type 2 diabetes without improving SH prediction. American Diabetes Association 2020-08 2020-05-15 /pmc/articles/PMC7372042/ /pubmed/32414887 http://dx.doi.org/10.2337/dc19-1791 Text en © 2020 by the American Diabetes Association https://www.diabetesjournals.org/content/licenseReaders may use this article as long as the work is properly cited, the use is educational and not for profit, and the work is not altered. More information is available at https://www.diabetesjournals.org/content/license. |
spellingShingle | Novel Communications in Diabetes Misra-Hebert, Anita D. Milinovich, Alex Zajichek, Alex Ji, Xinge Hobbs, Todd D. Weng, Wayne Petraro, Paul Kong, Sheldon X. Mocarski, Michelle Ganguly, Rahul Bauman, Janine M. Pantalone, Kevin M. Zimmerman, Robert S. Kattan, Michael W. Natural Language Processing Improves Detection of Nonsevere Hypoglycemia in Medical Records Versus Coding Alone in Patients With Type 2 Diabetes but Does Not Improve Prediction of Severe Hypoglycemia Events: An Analysis Using the Electronic Medical Record in a Large Health System |
title | Natural Language Processing Improves Detection of Nonsevere Hypoglycemia in Medical Records Versus Coding Alone in Patients With Type 2 Diabetes but Does Not Improve Prediction of Severe Hypoglycemia Events: An Analysis Using the Electronic Medical Record in a Large Health System |
title_full | Natural Language Processing Improves Detection of Nonsevere Hypoglycemia in Medical Records Versus Coding Alone in Patients With Type 2 Diabetes but Does Not Improve Prediction of Severe Hypoglycemia Events: An Analysis Using the Electronic Medical Record in a Large Health System |
title_fullStr | Natural Language Processing Improves Detection of Nonsevere Hypoglycemia in Medical Records Versus Coding Alone in Patients With Type 2 Diabetes but Does Not Improve Prediction of Severe Hypoglycemia Events: An Analysis Using the Electronic Medical Record in a Large Health System |
title_full_unstemmed | Natural Language Processing Improves Detection of Nonsevere Hypoglycemia in Medical Records Versus Coding Alone in Patients With Type 2 Diabetes but Does Not Improve Prediction of Severe Hypoglycemia Events: An Analysis Using the Electronic Medical Record in a Large Health System |
title_short | Natural Language Processing Improves Detection of Nonsevere Hypoglycemia in Medical Records Versus Coding Alone in Patients With Type 2 Diabetes but Does Not Improve Prediction of Severe Hypoglycemia Events: An Analysis Using the Electronic Medical Record in a Large Health System |
title_sort | natural language processing improves detection of nonsevere hypoglycemia in medical records versus coding alone in patients with type 2 diabetes but does not improve prediction of severe hypoglycemia events: an analysis using the electronic medical record in a large health system |
topic | Novel Communications in Diabetes |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7372042/ https://www.ncbi.nlm.nih.gov/pubmed/32414887 http://dx.doi.org/10.2337/dc19-1791 |
work_keys_str_mv | AT misrahebertanitad naturallanguageprocessingimprovesdetectionofnonseverehypoglycemiainmedicalrecordsversuscodingaloneinpatientswithtype2diabetesbutdoesnotimprovepredictionofseverehypoglycemiaeventsananalysisusingtheelectronicmedicalrecordinalargehealthsystem AT milinovichalex naturallanguageprocessingimprovesdetectionofnonseverehypoglycemiainmedicalrecordsversuscodingaloneinpatientswithtype2diabetesbutdoesnotimprovepredictionofseverehypoglycemiaeventsananalysisusingtheelectronicmedicalrecordinalargehealthsystem AT zajichekalex naturallanguageprocessingimprovesdetectionofnonseverehypoglycemiainmedicalrecordsversuscodingaloneinpatientswithtype2diabetesbutdoesnotimprovepredictionofseverehypoglycemiaeventsananalysisusingtheelectronicmedicalrecordinalargehealthsystem AT jixinge naturallanguageprocessingimprovesdetectionofnonseverehypoglycemiainmedicalrecordsversuscodingaloneinpatientswithtype2diabetesbutdoesnotimprovepredictionofseverehypoglycemiaeventsananalysisusingtheelectronicmedicalrecordinalargehealthsystem AT hobbstoddd naturallanguageprocessingimprovesdetectionofnonseverehypoglycemiainmedicalrecordsversuscodingaloneinpatientswithtype2diabetesbutdoesnotimprovepredictionofseverehypoglycemiaeventsananalysisusingtheelectronicmedicalrecordinalargehealthsystem AT wengwayne naturallanguageprocessingimprovesdetectionofnonseverehypoglycemiainmedicalrecordsversuscodingaloneinpatientswithtype2diabetesbutdoesnotimprovepredictionofseverehypoglycemiaeventsananalysisusingtheelectronicmedicalrecordinalargehealthsystem AT petraropaul naturallanguageprocessingimprovesdetectionofnonseverehypoglycemiainmedicalrecordsversuscodingaloneinpatientswithtype2diabetesbutdoesnotimprovepredictionofseverehypoglycemiaeventsananalysisusingtheelectronicmedicalrecordinalargehealthsystem AT kongsheldonx naturallanguageprocessingimprovesdetectionofnonseverehypoglycemiainmedicalrecordsversuscodingaloneinpatientswithtype2diabetesbutdoesnotimprovepredictionofseverehypoglycemiaeventsananalysisusingtheelectronicmedicalrecordinalargehealthsystem AT mocarskimichelle naturallanguageprocessingimprovesdetectionofnonseverehypoglycemiainmedicalrecordsversuscodingaloneinpatientswithtype2diabetesbutdoesnotimprovepredictionofseverehypoglycemiaeventsananalysisusingtheelectronicmedicalrecordinalargehealthsystem AT gangulyrahul naturallanguageprocessingimprovesdetectionofnonseverehypoglycemiainmedicalrecordsversuscodingaloneinpatientswithtype2diabetesbutdoesnotimprovepredictionofseverehypoglycemiaeventsananalysisusingtheelectronicmedicalrecordinalargehealthsystem AT baumanjaninem naturallanguageprocessingimprovesdetectionofnonseverehypoglycemiainmedicalrecordsversuscodingaloneinpatientswithtype2diabetesbutdoesnotimprovepredictionofseverehypoglycemiaeventsananalysisusingtheelectronicmedicalrecordinalargehealthsystem AT pantalonekevinm naturallanguageprocessingimprovesdetectionofnonseverehypoglycemiainmedicalrecordsversuscodingaloneinpatientswithtype2diabetesbutdoesnotimprovepredictionofseverehypoglycemiaeventsananalysisusingtheelectronicmedicalrecordinalargehealthsystem AT zimmermanroberts naturallanguageprocessingimprovesdetectionofnonseverehypoglycemiainmedicalrecordsversuscodingaloneinpatientswithtype2diabetesbutdoesnotimprovepredictionofseverehypoglycemiaeventsananalysisusingtheelectronicmedicalrecordinalargehealthsystem AT kattanmichaelw naturallanguageprocessingimprovesdetectionofnonseverehypoglycemiainmedicalrecordsversuscodingaloneinpatientswithtype2diabetesbutdoesnotimprovepredictionofseverehypoglycemiaeventsananalysisusingtheelectronicmedicalrecordinalargehealthsystem |