Cargando…
Natural Language Processing Enhances Prediction of Functional Outcome After Acute Ischemic Stroke
BACKGROUND: Conventional prognostic scores usually require predefined clinical variables to predict outcome. The advancement of natural language processing has made it feasible to derive meaning from unstructured data. We aimed to test whether using unstructured text in electronic health records can...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
John Wiley and Sons Inc.
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9075227/ https://www.ncbi.nlm.nih.gov/pubmed/34796719 http://dx.doi.org/10.1161/JAHA.121.023486 |
_version_ | 1784701634396291072 |
---|---|
author | Sung, Sheng‐Feng Chen, Chih‐Hao Pan, Ru‐Chiou Hu, Ya‐Han Jeng, Jiann‐Shing |
author_facet | Sung, Sheng‐Feng Chen, Chih‐Hao Pan, Ru‐Chiou Hu, Ya‐Han Jeng, Jiann‐Shing |
author_sort | Sung, Sheng‐Feng |
collection | PubMed |
description | BACKGROUND: Conventional prognostic scores usually require predefined clinical variables to predict outcome. The advancement of natural language processing has made it feasible to derive meaning from unstructured data. We aimed to test whether using unstructured text in electronic health records can improve the prediction of functional outcome after acute ischemic stroke. METHODS AND RESULTS: Patients hospitalized for acute ischemic stroke were identified from 2 hospital stroke registries (3847 and 2668 patients, respectively). Prediction models developed using the first cohort were externally validated using the second cohort, and vice versa. Free text in the history of present illness and computed tomography reports was used to build machine learning models using natural language processing to predict poor functional outcome at 90 days poststroke. Four conventional prognostic models were used as baseline models. The area under the receiver operating characteristic curves of the model using history of present illness in the internal and external validation sets were 0.820 and 0.792, respectively, which were comparable to the National Institutes of Health Stroke Scale score (0.811 and 0.807). The model using computed tomography reports achieved area under the receiver operating characteristic curves of 0.758 and 0.658. Adding information from clinical text significantly improved the predictive performance of each baseline model in terms of area under the receiver operating characteristic curves, net reclassification improvement, and integrated discrimination improvement indices (all P<0.001). Swapping the study cohorts led to similar results. CONCLUSIONS: By using natural language processing, unstructured text in electronic health records can provide an alternative tool for stroke prognostication, and even enhance the performance of existing prognostic scores. |
format | Online Article Text |
id | pubmed-9075227 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2021 |
publisher | John Wiley and Sons Inc. |
record_format | MEDLINE/PubMed |
spelling | pubmed-90752272022-05-10 Natural Language Processing Enhances Prediction of Functional Outcome After Acute Ischemic Stroke Sung, Sheng‐Feng Chen, Chih‐Hao Pan, Ru‐Chiou Hu, Ya‐Han Jeng, Jiann‐Shing J Am Heart Assoc Original Research BACKGROUND: Conventional prognostic scores usually require predefined clinical variables to predict outcome. The advancement of natural language processing has made it feasible to derive meaning from unstructured data. We aimed to test whether using unstructured text in electronic health records can improve the prediction of functional outcome after acute ischemic stroke. METHODS AND RESULTS: Patients hospitalized for acute ischemic stroke were identified from 2 hospital stroke registries (3847 and 2668 patients, respectively). Prediction models developed using the first cohort were externally validated using the second cohort, and vice versa. Free text in the history of present illness and computed tomography reports was used to build machine learning models using natural language processing to predict poor functional outcome at 90 days poststroke. Four conventional prognostic models were used as baseline models. The area under the receiver operating characteristic curves of the model using history of present illness in the internal and external validation sets were 0.820 and 0.792, respectively, which were comparable to the National Institutes of Health Stroke Scale score (0.811 and 0.807). The model using computed tomography reports achieved area under the receiver operating characteristic curves of 0.758 and 0.658. Adding information from clinical text significantly improved the predictive performance of each baseline model in terms of area under the receiver operating characteristic curves, net reclassification improvement, and integrated discrimination improvement indices (all P<0.001). Swapping the study cohorts led to similar results. CONCLUSIONS: By using natural language processing, unstructured text in electronic health records can provide an alternative tool for stroke prognostication, and even enhance the performance of existing prognostic scores. John Wiley and Sons Inc. 2021-11-19 /pmc/articles/PMC9075227/ /pubmed/34796719 http://dx.doi.org/10.1161/JAHA.121.023486 Text en © 2021 The Authors. Published on behalf of the American Heart Association, Inc., by Wiley. https://creativecommons.org/licenses/by-nc-nd/4.0/This is an open access article under the terms of the http://creativecommons.org/licenses/by-nc-nd/4.0/ (https://creativecommons.org/licenses/by-nc-nd/4.0/) License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non‐commercial and no modifications or adaptations are made. |
spellingShingle | Original Research Sung, Sheng‐Feng Chen, Chih‐Hao Pan, Ru‐Chiou Hu, Ya‐Han Jeng, Jiann‐Shing Natural Language Processing Enhances Prediction of Functional Outcome After Acute Ischemic Stroke |
title | Natural Language Processing Enhances Prediction of Functional Outcome After Acute Ischemic Stroke |
title_full | Natural Language Processing Enhances Prediction of Functional Outcome After Acute Ischemic Stroke |
title_fullStr | Natural Language Processing Enhances Prediction of Functional Outcome After Acute Ischemic Stroke |
title_full_unstemmed | Natural Language Processing Enhances Prediction of Functional Outcome After Acute Ischemic Stroke |
title_short | Natural Language Processing Enhances Prediction of Functional Outcome After Acute Ischemic Stroke |
title_sort | natural language processing enhances prediction of functional outcome after acute ischemic stroke |
topic | Original Research |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9075227/ https://www.ncbi.nlm.nih.gov/pubmed/34796719 http://dx.doi.org/10.1161/JAHA.121.023486 |
work_keys_str_mv | AT sungshengfeng naturallanguageprocessingenhancespredictionoffunctionaloutcomeafteracuteischemicstroke AT chenchihhao naturallanguageprocessingenhancespredictionoffunctionaloutcomeafteracuteischemicstroke AT panruchiou naturallanguageprocessingenhancespredictionoffunctionaloutcomeafteracuteischemicstroke AT huyahan naturallanguageprocessingenhancespredictionoffunctionaloutcomeafteracuteischemicstroke AT jengjiannshing naturallanguageprocessingenhancespredictionoffunctionaloutcomeafteracuteischemicstroke |